© 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. 105223
    Prev
    Next
    INDEX
    Explanations

    snippets of code related to functions and parameters

    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
    èŁ
    -0.07
    ANDLE
    -0.07
    deaux
    -0.07
    gili
    -0.06
    бо
    -0.06
    лÑİÑĩа
    -0.06
    _ALLOW
    -0.06
    лиÑĨ
    -0.06
    عت
    -0.06
    obb
    -0.06
    POSITIVE LOGITS
    ichert
    0.07
     Craw
    0.06
    scp
    0.06
     Barton
    0.06
     Sark
    0.06
     Cub
    0.06
    irthday
    0.06
    lyph
    0.05
    ACES
    0.05
    sj
    0.05
    Activations Density 0.049%

    No Known Activations