© 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. 108696
    Prev
    Next
    INDEX
    Explanations

    references to exceptions or unusual instances within a context

    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
    ýt
    -0.07
    lon
    -0.07
    isset
    -0.06
    liš
    -0.06
    ISS
    -0.06
    好äºĨ
    -0.06
    å¡«
    -0.06
    loops
    -0.06
     erg
    -0.06
    æķ¦
    -0.06
    POSITIVE LOGITS
     otherwise
    0.10
     none
    0.10
    otherwise
    0.09
     nobody
    0.09
     generally
    0.08
     pretty
    0.08
     largely
    0.08
    pretty
    0.08
     geen
    0.08
     Otherwise
    0.07
    Activations Density 0.016%

    No Known Activations