© 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. 69691
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences and expressions related to partitioning and similarity in structures

    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
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.06
    tablet
    -0.06
    tero
    -0.06
    pagen
    -0.06
    INGLE
    -0.06
    quette
    -0.06
    pars
    -0.06
    ingle
    -0.06
     Go
    -0.06
    abee
    -0.06
    POSITIVE LOGITS
    iny
    0.07
     ä¸ĸ
    0.07
    INY
    0.07
    æĩ
    0.06
    ilk
    0.06
    elry
    0.06
    ħ§
    0.06
     Vladim
    0.06
    .setViewport
    0.06
     eldre
    0.06
    Activations Density 0.102%

    No Known Activations