© 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. 17-LLAMASCOPE-RES-131K
    11. 87616
    Prev
    Next
    INDEX
    Explanations

    numerical representations or decimal values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -equiv
    -0.06
    reira
    -0.06
    353
    -0.06
     (
    -0.06
    908
    -0.06
    *
    -0.06
    827
    -0.05
    ä»ķ
    -0.05
    /tool
    -0.05
     rope
    -0.05
    POSITIVE LOGITS
    ิà¸Ļ
    0.08
     Buna
    0.08
    .ali
    0.08
     биÑĤ
    0.07
    Ïĩι
    0.07
     rodin
    0.07
     Meer
    0.07
    $lang
    0.07
    UDA
    0.07
     kdo
    0.07
    Activations Density 0.050%

    No Known Activations