© 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. 108863
    Prev
    Next
    INDEX
    Explanations

    details about product features and functionality

    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
    _DLL
    -0.07
    .external
    -0.07
     tÆ°á»Ľng
    -0.07
     outdoor
    -0.06
    _attached
    -0.06
    ysics
    -0.06
     Voll
    -0.06
    uros
    -0.06
    External
    -0.06
     External
    -0.06
    POSITIVE LOGITS
     inside
    0.17
     interior
    0.15
    inside
    0.15
     Inside
    0.14
    Inside
    0.14
     interiors
    0.13
     inner
    0.11
    _inside
    0.11
    åĨħ
    0.10
     Interior
    0.10
    Activations Density 0.020%

    No Known Activations