© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75124
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions related to health and diet

    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
    stab
    -0.07
    ενο
    -0.07
    ulp
    -0.07
    opus
    -0.07
    late
    -0.07
     Fog
    -0.07
    ạp
    -0.07
    angan
    -0.07
    .pivot
    -0.07
     Quý
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    0.07
    vk
    0.06
    ohn
    0.06
    bh
    0.06
    LK
    0.06
    edback
    0.06
    uset
    0.06
    #
    0.06
     benz
    0.06
    å·¥æ¥Ń
    0.06
    Activations Density 0.005%

    No Known Activations