© 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. 15-LLAMASCOPE-RES-131K
    11. 87191
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation and operator tokens within mathematical formulas, code syntax, or numerical expressions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    akhir
    -0.07
    laz
    -0.07
    idal
    -0.07
    enga
    -0.07
    uja
    -0.07
    alat
    -0.07
    iosper
    -0.07
    fik
    -0.07
    abox
    -0.07
    udas
    -0.07
    POSITIVE LOGITS
     meas
    0.06
    ë¦Ħ
    0.06
    inder
    0.06
     Sür
    0.06
    coder
    0.06
    plib
    0.06
    ì¶Ķ
    0.06
    LEC
    0.05
     رشتÙĩ
    0.05
     mes
    0.05
    Activations Density 0.256%

    No Known Activations