© 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. 28019
    Prev
    Next
    INDEX
    Explanations

    references to evaluating and questioning decisions

    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
    quate
    -0.07
     current
    -0.06
     squat
    -0.06
    íı
    -0.06
     Zig
    -0.06
    izik
    -0.06
    reh
    -0.06
     simplified
    -0.05
    .logic
    -0.05
    /cop
    -0.05
    POSITIVE LOGITS
    ogo
    0.07
     Ahmet
    0.07
    ÑģÑĤе
    0.07
    _INITIALIZER
    0.06
    wang
    0.06
    üst
    0.06
     Goodman
    0.06
    ÅĻÃŃ
    0.06
     ÙĤرار
    0.06
    .jd
    0.06
    Activations Density 0.000%

    No Known Activations