© 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. 105358
    Prev
    Next
    INDEX
    Explanations

    words associated with value and worth

    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
    oran
    -0.07
    ocha
    -0.07
    orque
    -0.07
    pek
    -0.06
     bitwise
    -0.06
    ázd
    -0.06
    تÙĤ
    -0.06
    ensex
    -0.06
     беÑģ
    -0.06
    YRO
    -0.06
    POSITIVE LOGITS
    ibil
    0.07
    ulum
    0.07
    ik
    0.07
     specialization
    0.06
    geois
    0.06
    333
    0.06
     Nes
    0.06
     sorts
    0.06
    enstein
    0.06
     vivid
    0.06
    Activations Density 0.000%

    No Known Activations