Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77099
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and coding structures

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

    Programming syntax elements such as delimiters, punctuation, and structural keywords that are essential for proper code parsing across various languages.

    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
     a
    -0.07
     to
    -0.06
     de
    -0.06
    ilk
    -0.05
     for
    -0.05
     at
    -0.05
     t
    -0.05
     -
    -0.05
     s
    -0.05
     u
    -0.05
    POSITIVE LOGITS
    å¡ļ
    0.09
    intColor
    0.09
     anale
    0.08
     addCriterion
    0.08
    actionDate
    0.08
    ?option
    0.08
    biên
    0.08
    pedia
    0.08
    ÑĮко
    0.08
    ãĤĩãģĨ
    0.08
    Activations Density 0.590%

    No Known Activations