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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 299
    Prev
    Next
    INDEX
    Explanations

    terms related to numerological systems and their analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olik
    -0.15
    aku
    -0.15
    yll
    -0.15
    reak
    -0.14
    ť
    -0.14
    rox
    -0.14
     intersection
    -0.14
     SAL
    -0.13
     elastic
    -0.13
    ::*
    -0.13
    POSITIVE LOGITS
    chwitz
    0.17
    adesh
    0.17
     corrections
    0.16
     Merk
    0.16
    midd
    0.16
     correction
    0.16
     vess
    0.16
    ibur
    0.15
     midd
    0.15
    unya
    0.15
    Activations Density 0.034%

    No Known Activations