© 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. 9-LLAMASCOPE-RES-131K
    11. 96320
    Prev
    Next
    INDEX
    Explanations

    code-related terms and components in a programming context

    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
    tuk
    -0.07
     ä»Ĭ
    -0.06
    dent
    -0.06
    isque
    -0.06
    eyin
    -0.06
    soc
    -0.06
    iel
    -0.06
    tol
    -0.06
    °ëĭ¤
    -0.06
     Ø®ÛĮ
    -0.06
    POSITIVE LOGITS
    \widgets
    0.07
    _echo
    0.07
    .gov
    0.07
    orias
    0.06
    WithValue
    0.06
    .setDefault
    0.06
    athan
    0.06
    ितन
    0.06
    ufacturer
    0.06
    thr
    0.06
    Activations Density 0.017%

    No Known Activations