© 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. 17-LLAMASCOPE-RES-131K
    6. 78125
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
    ARAM
    -0.08
    PROTO
    -0.07
    thal
    -0.07
     Rencontre
    -0.07
    /*@
    -0.06
    ì§ĢìļĶ
    -0.06
    anje
    -0.06
     coordin
    -0.06
    _utf
    -0.06
    zar
    -0.06
    POSITIVE LOGITS
    ãĥ»ãĥ»ãĥ»↵↵
    0.07
    asp
    0.07
    osti
    0.06
    ...↵↵↵↵↵↵
    0.06
    adt
    0.06
    aterno
    0.06
    odom
    0.06
    â̦↵↵↵↵
    0.06
    ?↵↵↵↵↵↵
    0.06
    leck
    0.06
    Activations Density 0.000%

    No Known Activations