© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 23014
    Prev
    Next
    INDEX
    Explanations

    information related to social security benefits and payments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical data in formal or technical documents, particularly those containing statistics, dates, measurements, or official reports.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    formal, data-heavy announcements reporting increases/decreases, amounts, dates, and beneficiaries in government or economic contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .subplots
    -0.16
    aná
    -0.15
    ajan
    -0.14
    оÑĤÑĮ
    -0.14
    GV
    -0.13
    ãģªãĤĭ
    -0.13
    ancia
    -0.13
     Tal
    -0.13
     Tee
    -0.13
    arb
    -0.13
    POSITIVE LOGITS
    tent
    0.18
    icable
    0.14
    znik
    0.14
    ίκ
    0.14
    detach
    0.14
    ãİ
    0.13
    eid
    0.13
     Rainbow
    0.13
     diplom
    0.13
    .findIndex
    0.13
    Activations Density 0.006%

    No Known Activations