© 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. 103868
    Prev
    Next
    INDEX
    Explanations

    references to celebrations, events, and milestones

    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
    rv
    -0.07
     after
    -0.07
     then
    -0.06
     fail
    -0.06
     inter
    -0.06
     in
    -0.06
     wr
    -0.06
    idget
    -0.05
     exc
    -0.05
     when
    -0.05
    POSITIVE LOGITS
    ÄŁÃ¼
    0.08
     hãy
    0.08
    DataExchange
    0.08
    >NN
    0.08
    ectl
    0.08
    ATIO
    0.08
    ieu
    0.08
    @nate
    0.08
    /Peak
    0.08
    STALL
    0.08
    Activations Density 0.015%

    No Known Activations