© 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. 54680
    Prev
    Next
    INDEX
    Explanations

    genre labels and categories in the text

    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
    loff
    -0.07
    ords
    -0.07
    XL
    -0.06
    iversal
    -0.06
    rete
    -0.06
    tainment
    -0.06
    eut
    -0.06
    .Îij
    -0.06
    _Abstract
    -0.06
    atron
    -0.06
    POSITIVE LOGITS
     Prospect
    0.06
    avar
    0.06
    ess
    0.06
     altına
    0.06
    wis
    0.06
    nid
    0.06
     Lever
    0.06
    DCF
    0.06
    bjerg
    0.06
    ighton
    0.06
    Activations Density 0.001%

    No Known Activations