© 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. 124206
    Prev
    Next
    INDEX
    Explanations

    coding patterns and configurations in programming 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
    rane
    -0.06
    expo
    -0.06
    ebo
    -0.06
    posium
    -0.06
    'gc
    -0.06
    elry
    -0.06
    .RightToLeft
    -0.06
    hof
    -0.06
    hunter
    -0.06
    pst
    -0.06
    POSITIVE LOGITS
    #ad
    0.07
     location
    0.07
    unga
    0.06
     Ulus
    0.06
     root
    0.06
     Gerr
    0.06
     Batter
    0.06
    ullet
    0.06
     downtown
    0.06
     elsewhere
    0.06
    Activations Density 0.010%

    No Known Activations