© 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 EvalsExportsAPI 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. 119242
    Prev
    Next
    INDEX
    Explanations

    statistical information related to manufacturing and materials

    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
    otts
    -0.08
    blings
    -0.07
    uela
    -0.06
    undler
    -0.06
    orian
    -0.06
    pus
    -0.06
    ulse
    -0.06
    rawn
    -0.06
    umbed
    -0.06
    ecess
    -0.06
    POSITIVE LOGITS
    kker
    0.07
    985
    0.06
     Tub
    0.06
     tub
    0.06
    .prof
    0.06
     seni
    0.06
    attice
    0.06
    è£ķ
    0.06
    ERT
    0.05
     BOOL
    0.05
    Activations Density 0.005%

    No Known Activations