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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71495
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific programming commands or functions related to system operations and network tasks

    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
    ymph
    -0.07
    /OR
    -0.07
     Shen
    -0.07
     çĭ
    -0.07
    iais
    -0.07
    è¥
    -0.06
    аÑĢод
    -0.06
    fillType
    -0.06
    iaux
    -0.06
    [".
    -0.06
    POSITIVE LOGITS
    ache
    0.07
    uto
    0.06
    ero
    0.06
     capt
    0.06
    ries
    0.06
    ://
    0.06
    _easy
    0.06
     Eastern
    0.06
    raction
    0.05
    amic
    0.05
    Activations Density 0.035%

    No Known Activations