© 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. 4673
    Prev
    Next
    INDEX
    Explanations

    references to programming frameworks or libraries

    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
    imer
    -0.07
    ern
    -0.06
    pag
    -0.06
    ombok
    -0.06
    å¹¹ç·ļ
    -0.06
    quam
    -0.06
     ry
    -0.06
     nig
    -0.06
     pog
    -0.06
    cher
    -0.06
    POSITIVE LOGITS
    \Component
    0.10
    zee
    0.08
    Ø®ÛĮ
    0.07
    anness
    0.07
    ergic
    0.07
    ÛĮز
    0.07
    onds
    0.07
    asal
    0.07
    urd
    0.07
    monds
    0.07
    Activations Density 0.000%

    No Known Activations