© 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. 15-LLAMASCOPE-RES-131K
    11. 86232
    Prev
    Next
    INDEX
    Explanations

    document formatting cues and structure

    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
     Blaze
    -0.06
     sin
    -0.06
    sonian
    -0.05
    ume
    -0.05
    ai
    -0.05
    Ñīин
    -0.05
    ory
    -0.05
     this
    -0.05
    ëŁī
    -0.05
    isse
    -0.05
    POSITIVE LOGITS
    StandardItem
    0.07
    ivatel
    0.07
     ----------------------------------------------------------------------↵
    0.06
    sah
    0.06
     -------------------------------------------------------------------------↵
    0.06
    okoj
    0.06
    ="__
    0.06
    	TokenName
    0.06
    ÄĽ
    0.06
    ,'#
    0.06
    Activations Density 0.000%

    No Known Activations