© 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. 39407
    Prev
    Next
    INDEX
    Explanations

    inquiries and questions about various subjects

    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
    ichert
    -0.07
    ibName
    -0.06
    creativecommons
    -0.06
    olini
    -0.06
     Dit
    -0.06
     Rice
    -0.06
    OfSize
    -0.06
     Silk
    -0.06
    rote
    -0.06
    SeekBar
    -0.05
    POSITIVE LOGITS
     tedy
    0.08
    ething
    0.08
    åij¢
    0.07
    ?
    0.07
    ære
    0.07
    eka
    0.07
    _DIRECT
    0.07
     же
    0.07
    ledo
    0.07
    ses
    0.06
    Activations Density 0.031%

    No Known Activations