© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89851
    Prev
    Next
    INDEX
    Explanations

    contextual phrases indicating specific conditions or scenarios

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Weather
    -0.07
    ̧
    -0.07
     weather
    -0.07
     CString
    -0.06
     however
    -0.06
     chatte
    -0.06
    adera
    -0.06
    aar
    -0.06
    elligent
    -0.06
     trouble
    -0.06
    POSITIVE LOGITS
    ä¹İ
    0.07
    oten
    0.06
    cone
    0.06
    jac
    0.06
     tedy
    0.06
    amo
    0.06
    595
    0.06
    isci
    0.06
    veau
    0.06
    arken
    0.06
    Activations Density 0.026%

    No Known Activations