© 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. 5-LLAMASCOPE-RES-131K
    6. 126133
    Prev
    Next
    INDEX
    Explanations

    mentions of conversations

    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
    ura
    -0.08
    ched
    -0.07
    aging
    -0.07
     Hudson
    -0.06
    ritz
    -0.06
    ow
    -0.06
    intosh
    -0.06
     Han
    -0.06
    ù
    -0.06
    chen
    -0.06
    POSITIVE LOGITS
    onn
    0.08
    ariat
    0.07
     LIABLE
    0.07
    aire
    0.07
    mani
    0.07
    EIF
    0.07
    ISTA
    0.07
    ÄĽst
    0.06
    isex
    0.06
    imals
    0.06
    Activations Density 0.008%

    No Known Activations