© 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. 57500
    Prev
    Next
    INDEX
    Explanations

    key moments and scoring events in competitive games

    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
     league
    -0.06
    issance
    -0.06
    nk
    -0.06
    aser
    -0.06
    :
    -0.06
     warrant
    -0.06
    arel
    -0.06
    odos
    -0.06
    unks
    -0.06
    au
    -0.06
    POSITIVE LOGITS
    Cipher
    0.07
    ëĭ´
    0.07
    à¸Ŀ
    0.07
     PageInfo
    0.07
    XObject
    0.07
    steen
    0.07
    ë²Ķ
    0.07
     è¢
    0.07
    YTE
    0.07
    cipher
    0.07
    Activations Density 0.005%

    No Known Activations