© 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. 38231
    Prev
    Next
    INDEX
    Explanations

    discussions of time and planning

    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
    alama
    -0.07
    ictor
    -0.06
    %B
    -0.06
    ÌĨ
    -0.06
    unos
    -0.06
    lero
    -0.06
    _formats
    -0.06
    eyed
    -0.06
    ỹ
    -0.06
    peÄį
    -0.05
    POSITIVE LOGITS
     Shelter
    0.07
    екаÑĢ
    0.07
    otel
    0.07
    afen
    0.07
    ernet
    0.07
    distance
    0.07
     distance
    0.07
     Distance
    0.07
    ги
    0.07
    æ³Ĭ
    0.06
    Activations Density 0.011%

    No Known Activations