© 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. 104787
    Prev
    Next
    INDEX
    Explanations

    symbols and syntax used in programming and scripting languages

    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
    isin
    -0.08
    irl
    -0.08
    lazy
    -0.07
    upplier
    -0.06
    ocommerce
    -0.06
    -Ñģ
    -0.06
    iffin
    -0.06
    ubit
    -0.06
    shortcode
    -0.06
    rieg
    -0.06
    POSITIVE LOGITS
     Richardson
    0.07
     intptr
    0.07
     Grove
    0.07
    GOR
    0.06
     Swinger
    0.06
    lyn
    0.06
    rette
    0.06
    379
    0.06
    à¸Ĥà¸ĵะà¸Ĺ
    0.06
     Gore
    0.06
    Activations Density 0.001%

    No Known Activations