© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 93119
    Prev
    Next
    INDEX
    Explanations

    conjunctions and expressions of contrast

    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
    ickle
    -0.07
    :animated
    -0.07
    εÏħ
    -0.06
    ones
    -0.06
    odes
    -0.06
    à¸ģลาà¸ĩ
    -0.06
    .Encoding
    -0.06
    essa
    -0.06
    ook
    -0.06
    ç´Ķ
    -0.06
    POSITIVE LOGITS
    CS
    0.07
    estre
    0.07
     âĨĴ↵↵
    0.07
    antz
    0.06
    Ī¬
    0.06
    FormField
    0.06
     Kaw
    0.06
    efa
    0.06
     OPS
    0.06
    رÙĤ
    0.06
    Activations Density 0.003%

    No Known Activations