© 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. 94569
    Prev
    Next
    INDEX
    Explanations

    numeric data or statistical information

    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
     ball
    -0.06
    azzo
    -0.06
     Kab
    -0.06
    eya
    -0.06
     Apt
    -0.06
     Ball
    -0.06
     ext
    -0.05
     rec
    -0.05
    or
    -0.05
     Kan
    -0.05
    POSITIVE LOGITS
     metic
    0.08
    isay
    0.07
     chung
    0.07
     kles
    0.07
    egrator
    0.07
    èģ
    0.07
    åĿ¡
    0.07
    autoreleasepool
    0.07
    remen
    0.07
    -scrollbar
    0.07
    Activations Density 0.000%

    No Known Activations