© 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. 73375
    Prev
    Next
    INDEX
    Explanations

    references to comparison and categorization of items or concepts

    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
    ennen
    -0.07
    ipc
    -0.07
    iez
    -0.06
    جب
    -0.06
    ElapsedTime
    -0.06
    utral
    -0.06
    ngen
    -0.06
    ãģĭãģij
    -0.06
    uga
    -0.06
    adero
    -0.06
    POSITIVE LOGITS
     ones
    0.15
     stuff
    0.09
     Ones
    0.08
    оÑĢов
    0.07
     thing
    0.07
    ething
    0.07
    ãĤĤãģ®
    0.07
     olanlar
    0.06
    ÑĢоÑĩ
    0.06
     ê²ĥ
    0.06
    Activations Density 0.038%

    No Known Activations