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

    Neuronpedia

    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. 4339
    Prev
    Next
    INDEX
    Explanations

    references to error messages or programming documentation

    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
    abor
    -0.06
    ulus
    -0.06
     sme
    -0.06
    од
    -0.06
     Affairs
    -0.05
    uky
    -0.05
    utr
    -0.05
    lim
    -0.05
    -css
    -0.05
    cin
    -0.05
    POSITIVE LOGITS
    AndHashCode
    0.08
    /Peak
    0.07
    inski
    0.07
    owski
    0.07
    ADF
    0.07
    ujet
    0.07
    ystack
    0.07
    _marshall
    0.07
    ardown
    0.07
    Å¡ak
    0.07
    Activations Density 0.000%

    No Known Activations