© 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. 104779
    Prev
    Next
    INDEX
    Explanations

    references to public access or public information

    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
    inton
    -0.06
    478
    -0.06
    ilton
    -0.06
    358
    -0.06
    ph
    -0.06
     bol
    -0.06
    otron
    -0.06
    ov
    -0.06
     Barton
    -0.06
    618
    -0.05
    POSITIVE LOGITS
     "-//
    0.09
    pector
    0.08
    коп
    0.08
    IZER
    0.08
    лиÑĨ
    0.07
    abras
    0.07
    .nan
    0.07
    istik
    0.07
    PILE
    0.07
    obili
    0.06
    Activations Density 0.014%

    No Known Activations