© 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. 9-LLAMASCOPE-RES-131K
    11. 97903
    Prev
    Next
    INDEX
    Explanations

    references to places and facilities related to education and confinement

    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
    <=$
    -0.09
    .liferay
    -0.07
    ][_
    -0.07
    igkeit
    -0.07
    ilib
    -0.07
    ater
    -0.06
    wiÄħ
    -0.06
    elm
    -0.06
     ilma
    -0.06
    -terminal
    -0.06
    POSITIVE LOGITS
    408
    0.07
    au
    0.07
    278
    0.06
    oring
    0.06
    enate
    0.06
     residuals
    0.06
    uze
    0.06
     اÙĦاج
    0.06
    зн
    0.06
    gems
    0.06
    Activations Density 0.186%

    No Known Activations