Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106178
    Prev
    Next
    INDEX
    Explanations

    proper nouns relating to people and places in the context of sports and finance

    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
     together
    -0.07
    inel
    -0.07
    cade
    -0.07
    ÙĤد
    -0.06
    ugas
    -0.06
    rede
    -0.06
     inf
    -0.06
    _defs
    -0.06
     Narrative
    -0.06
     Heck
    -0.06
    POSITIVE LOGITS
     whom
    0.08
     who
    0.08
     whose
    0.08
    roti
    0.07
    who
    0.07
     Pension
    0.07
     który
    0.06
     коÑĤоÑĢÑĭй
    0.06
    whose
    0.06
    .ContentAlignment
    0.06
    Activations Density 0.018%

    No Known Activations