© 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. 57687
    Prev
    Next
    INDEX
    Explanations

    reports or statements with significant emphasis on citing individuals' opinions or assertions

    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
    inery
    -0.06
    iri
    -0.06
    ien
    -0.06
    onna
    -0.06
    iene
    -0.06
    uve
    -0.06
    fab
    -0.06
    izzo
    -0.06
     Lancaster
    -0.06
    öst
    -0.06
    POSITIVE LOGITS
    èĩªå·±
    0.07
     himself
    0.07
     ÑģебÑı
    0.06
    URRENT
    0.06
     his
    0.06
     ank
    0.06
     ÑģвоÑİ
    0.06
    bove
    0.06
    ype
    0.06
    Ñĸд
    0.06
    Activations Density 0.034%

    No Known Activations