© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 2612
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or references related to financial metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agu
    -0.17
    ostel
    -0.16
    Ñıл
    -0.14
    zek
    -0.14
     strip
    -0.14
    ứ
    -0.14
     herald
    -0.14
    ipel
    -0.14
     Barg
    -0.14
    ekler
    -0.14
    POSITIVE LOGITS
    泡
    0.15
    owitz
    0.15
     eo
    0.15
    èĻİ
    0.14
    tent
    0.14
    depend
    0.14
    AGMA
    0.14
    deen
    0.13
    cum
    0.13
     GOODMAN
    0.13
    Activations Density 0.057%

    No Known Activations