© 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. 121463
    Prev
    Next
    INDEX
    Explanations

    instances of unresolved issues or errors in a technical 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
    inn
    -0.06
    isen
    -0.06
     companion
    -0.06
    conc
    -0.06
    uzzle
    -0.06
    iral
    -0.06
     toler
    -0.06
     Rag
    -0.05
     Contrib
    -0.05
    -component
    -0.05
    POSITIVE LOGITS
     same
    0.13
    same
    0.12
    Same
    0.10
    _same
    0.10
     Same
    0.10
    SAME
    0.09
     still
    0.09
     ëĺ
    0.09
     SAME
    0.09
     STILL
    0.09
    Activations Density 0.007%

    No Known Activations