© 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. 9-LLAMASCOPE-RES-131K
    6. 95498
    Prev
    Next
    INDEX
    Explanations

    references to personal choices or selections

    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
    taire
    -0.07
    argas
    -0.06
    rea
    -0.06
    hunter
    -0.06
    mb
    -0.06
     è¡
    -0.06
    antino
    -0.06
    utral
    -0.06
     twig
    -0.06
    Ñĥл
    -0.06
    POSITIVE LOGITS
     chosen
    0.08
    chosen
    0.07
     gó
    0.07
    ä»ĭ
    0.06
    ouse
    0.06
    umas
    0.06
     choice
    0.06
    olls
    0.06
    /request
    0.06
    âĸij
    0.06
    Activations Density 0.008%

    No Known Activations