© 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 EvalsExportsAPI 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. 84039
    Prev
    Next
    INDEX
    Explanations

    instances of errors and mistakes

    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
    ierz
    -0.07
    loub
    -0.07
    åŀ
    -0.07
     Lester
    -0.06
    ÑĢиз
    -0.06
    mw
    -0.06
    rose
    -0.06
     Flores
    -0.06
    UNUSED
    -0.06
    ENS
    -0.06
    POSITIVE LOGITS
    /error
    0.09
    /errors
    0.09
     mistakes
    0.08
    Made
    0.07
    iveness
    0.07
     error
    0.07
    -made
    0.07
     mistake
    0.07
     rect
    0.07
    bote
    0.07
    Activations Density 0.017%

    No Known Activations