© 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. 87538
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and code structure elements

    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
    atrice
    -0.06
    aster
    -0.06
    antee
    -0.06
    crast
    -0.06
    ecast
    -0.06
    lette
    -0.06
    ysa
    -0.06
    ague
    -0.06
    velle
    -0.06
    556
    -0.06
    POSITIVE LOGITS
    rog
    0.09
    gres
    0.07
    çķ¥
    0.06
    //{{
    0.06
    dos
    0.06
    éry
    0.06
    ifié
    0.06
    DEX
    0.06
    inalg
    0.06
    RIA
    0.06
    Activations Density 0.000%

    No Known Activations