© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27421
    Prev
    Next
    INDEX
    Explanations

    code structures and their components, particularly those related to function definitions and return statements

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

    Function argument syntax and tuple structures in various programming languages, particularly paired parentheses, brackets, or other delimiters that enclose parameters, followed by operators like equals signs or commas.

    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
    instanc
    -0.06
    ourg
    -0.06
     Challenger
    -0.06
    ç§ijæĬĢæľīéĻIJåħ¬åı¸
    -0.06
     Alvarez
    -0.06
     ali
    -0.06
    pz
    -0.06
    oc
    -0.06
    amel
    -0.06
    İĺìĿ´
    -0.06
    POSITIVE LOGITS
     pair
    0.08
     pairs
    0.08
    égor
    0.08
     tuple
    0.07
     íĬ
    0.07
     Tuple
    0.07
    .pair
    0.06
     Äijôi
    0.06
     Pair
    0.06
    -gun
    0.06
    Activations Density 0.128%

    No Known Activations