© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107313
    Prev
    Next
    INDEX
    Explanations

    quantifiable terms related to fees, payments, or counts in various contexts

    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
    buch
    -0.07
    upy
    -0.07
    ombat
    -0.07
    iali
    -0.07
    udeau
    -0.07
     soud
    -0.07
    iversit
    -0.07
     Garrison
    -0.07
    utsch
    -0.07
    rung
    -0.07
    POSITIVE LOGITS
     perch
    0.06
    ience
    0.06
     covered
    0.06
     Roc
    0.05
    ood
    0.05
    ay
    0.05
     affected
    0.05
    emax
    0.05
     staff
    0.05
    OOD
    0.05
    Activations Density 0.019%

    No Known Activations