© 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. 126429
    Prev
    Next
    INDEX
    Explanations

    actions and states related to activity and engagement

    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
    ANTE
    -0.08
    ики
    -0.08
    ï
    -0.07
    pyx
    -0.07
    BITS
    -0.07
     Laden
    -0.07
    REA
    -0.07
    vice
    -0.07
    CEED
    -0.07
     rencont
    -0.07
    POSITIVE LOGITS
     anyone
    0.08
     oneself
    0.08
     easily
    0.07
    aign
    0.07
    cene
    0.06
    md
    0.06
     Easily
    0.06
     anybody
    0.06
    OGLE
    0.06
     Anyone
    0.06
    Activations Density 0.050%

    No Known Activations