© 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. 85132
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and equations

    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
    onta
    -0.08
    eton
    -0.06
    ãĤ«ãĥ¼
    -0.06
     cul
    -0.06
    ÙĪÛĮÛĮ
    -0.06
     uncon
    -0.06
    Enlarge
    -0.06
    $title
    -0.06
    azen
    -0.06
    erglass
    -0.06
    POSITIVE LOGITS
    yas
    0.08
     transformed
    0.07
     transform
    0.07
    transform
    0.07
    -transform
    0.07
    edes
    0.07
    inge
    0.06
    enko
    0.06
    _TRANSFORM
    0.06
    bard
    0.06
    Activations Density 0.119%

    No Known Activations