© 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. 56381
    Prev
    Next
    INDEX
    Explanations

    occurrences of user-related terms and identifiers

    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
    serie
    -0.07
    /use
    -0.07
    UserProfile
    -0.07
    uan
    -0.07
     Turtle
    -0.06
    ser
    -0.06
    aque
    -0.06
    gren
    -0.06
    scription
    -0.06
    _TRA
    -0.06
    POSITIVE LOGITS
    baugh
    0.09
    mtree
    0.08
    stamp
    0.08
    elik
    0.08
    fare
    0.07
    ãĥ¼ãĤ¹ãĥĪ
    0.07
    -friendly
    0.07
    729
    0.07
    InteractionEnabled
    0.07
    veal
    0.07
    Activations Density 0.017%

    No Known Activations