© 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. 57742
    Prev
    Next
    INDEX
    Explanations

    terms related to health and safety protocols in the context of community welfare

    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
    frey
    -0.06
    ippo
    -0.06
     BUFFER
    -0.06
     Jon
    -0.06
    lossen
    -0.06
    bens
    -0.06
    ajan
    -0.06
     Buffer
    -0.06
     stabil
    -0.06
    Jon
    -0.06
    POSITIVE LOGITS
    Transmission
    0.07
     our
    0.06
    .Member
    0.06
    ayet
    0.06
     transmission
    0.06
    ourd
    0.06
    itre
    0.06
    olini
    0.06
    upplier
    0.06
    ewood
    0.06
    Activations Density 0.006%

    No Known Activations