© 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. 15377
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting conventions in text

    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
    anh
    -0.08
    adol
    -0.07
    449
    -0.07
    -0.07
    anz
    -0.07
    499
    -0.07
    ylie
    -0.06
    549
    -0.06
    Ìĥ
    -0.06
     Pruitt
    -0.06
    POSITIVE LOGITS
    á»Ļ
    0.06
     OMX
    0.06
    ollider
    0.06
    aries
    0.06
    ottes
    0.06
    ög
    0.06
     masse
    0.06
    landers
    0.06
    _REASON
    0.06
     гÑĢÑĥ
    0.06
    Activations Density 0.037%

    No Known Activations