© 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. 120607
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbial forms that describe qualities or characteristics

    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
    avez
    -0.08
    /we
    -0.08
    afs
    -0.08
    ixo
    -0.07
    ereum
    -0.07
     erót
    -0.07
    erville
    -0.07
    909
    -0.07
    onte
    -0.07
    uld
    -0.07
    POSITIVE LOGITS
     speaking
    0.09
    -speaking
    0.08
    -wise
    0.07
    /math
    0.07
     Speaking
    0.07
    æĸ¹éĿ¢
    0.06
    Speaking
    0.06
     it
    0.06
    ä¸ĬçļĦ
    0.06
    orden
    0.06
    Activations Density 0.023%

    No Known Activations