© 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. 17338
    Prev
    Next
    INDEX
    Explanations

    numerical values or figures, particularly related to measurements or data points

    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
    earer
    -0.07
    _Lean
    -0.07
    olio
    -0.07
    ĵåIJį
    -0.07
    oub
    -0.07
    ount
    -0.07
    icket
    -0.06
    dül
    -0.06
    desk
    -0.06
    extView
    -0.06
    POSITIVE LOGITS
     Machines
    0.07
    riel
    0.06
    ÑĥÑĩа
    0.06
     machines
    0.06
     league
    0.06
     completeness
    0.06
    wand
    0.06
    UC
    0.06
     Compared
    0.06
    asz
    0.05
    Activations Density 0.000%

    No Known Activations