© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41961
    Prev
    Next
    INDEX
    Explanations

    references to bugs or issues in software development

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    reuse
    -0.08
    Reuse
    -0.08
    quarter
    -0.07
    inder
    -0.07
    lich
    -0.07
    ÃŃch
    -0.07
    _RESP
    -0.07
    affer
    -0.06
    _icons
    -0.06
    achs
    -0.06
    POSITIVE LOGITS
     workaround
    0.10
     Solution
    0.08
     Cul
    0.08
     solution
    0.08
    Solution
    0.08
     SOLUTION
    0.07
    solution
    0.07
    (solution
    0.07
    解åĨ³
    0.07
     fix
    0.07
    Activations Density 0.023%

    No Known Activations