© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 104309
    Prev
    Next
    INDEX
    Explanations

    programming-related errors and class references in Java

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

    The token(s) that specify specific values, parameters, or syntactic elements in technical code, syntax, or commands - often related to function names, operators, parameter values, or language-specific syntax that would be crucial for correct execution.

    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
    ival
    -0.07
    rint
    -0.06
    bourg
    -0.06
    azzo
    -0.06
     Haram
    -0.06
    ught
    -0.05
    engo
    -0.05
    IVAL
    -0.05
    kovi
    -0.05
    atham
    -0.05
    POSITIVE LOGITS
    æģĴ
    0.07
    æ³ķ人
    0.07
     ëĭ
    0.07
    ãĥ«ãĥī
    0.07
     pied
    0.06
     inse
    0.06
    //===
    0.06
    //{{
    0.06
    ÙħÙĪØ¯
    0.06
     spl
    0.06
    Activations Density 0.004%

    No Known Activations