© 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. 42234
    Prev
    Next
    INDEX
    Explanations

    expressions related to programming or computer science 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
    νο
    -0.08
    yny
    -0.07
    ereg
    -0.07
    UFFIX
    -0.07
    207
    -0.07
    ipple
    -0.07
    ARGIN
    -0.07
    endon
    -0.06
    aled
    -0.06
    elters
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.08
    ties
    0.06
    RIPT
    0.06
    atu
    0.06
    ınca
    0.06
     incon
    0.06
    impse
    0.06
     points
    0.06
    вÑĸ
    0.06
     Carpenter
    0.06
    Activations Density 0.000%

    No Known Activations