© 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. 119095
    Prev
    Next
    INDEX
    Explanations

    references to people or personal relationships

    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
     currently
    -0.07
    Łèĥ½
    -0.07
     Lore
    -0.06
    alars
    -0.06
     Resolver
    -0.06
    chie
    -0.06
    currently
    -0.06
    200
    -0.06
    783
    -0.05
    iect
    -0.05
    POSITIVE LOGITS
    Radians
    0.07
    ÅĻez
    0.07
    /ajax
    0.06
    ë°Ģ
    0.06
    रण
    0.06
    елей
    0.06
     witness
    0.06
    .hxx
    0.06
    -helper
    0.06
    ença
    0.06
    Activations Density 0.000%

    No Known Activations