© 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. 94848
    Prev
    Next
    INDEX
    Explanations

    references to positive or negative outcomes

    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
    places
    -0.08
    esters
    -0.08
    ientos
    -0.08
    za
    -0.07
    exion
    -0.07
     Erk
    -0.07
    -eyed
    -0.07
    tur
    -0.07
    iser
    -0.06
    quette
    -0.06
    POSITIVE LOGITS
    /down
    0.12
    -down
    0.08
    invert
    0.07
    /out
    0.07
    /up
    0.07
     invert
    0.07
    gam
    0.07
     commas
    0.06
     latter
    0.06
    attery
    0.06
    Activations Density 0.002%

    No Known Activations