© 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. 117399
    Prev
    Next
    INDEX
    Explanations

    references to JSON data format and related content types

    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
    reu
    -0.08
    _UNUSED
    -0.07
    eut
    -0.06
    nesty
    -0.06
    ÑĩаÑģно
    -0.06
    esser
    -0.06
    asal
    -0.06
    preci
    -0.06
    Ñģлов
    -0.06
    rary
    -0.06
    POSITIVE LOGITS
    ;charset
    0.08
    +xml
    0.08
     dol
    0.08
     Dol
    0.07
    dol
    0.07
    odia
    0.06
    à¥
    0.06
    /by
    0.06
    ;base
    0.06
     Innov
    0.06
    Activations Density 0.002%

    No Known Activations