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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 88637
    Prev
    Next
    INDEX
    Explanations

    data structures and their manipulation in programming contexts

    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
     underst
    -0.06
    -
    -0.06
     weather
    -0.06
     drain
    -0.06
    xic
    -0.06
     Nes
    -0.06
     Apr
    -0.06
    TOOLS
    -0.06
    usat
    -0.06
    ropp
    -0.06
    POSITIVE LOGITS
    OfClass
    0.07
    _lineno
    0.07
    ÐĶÐļ
    0.07
    ICODE
    0.07
    ATUS
    0.07
    ìĭľìĺ¤
    0.07
    edBy
    0.07
    oves
    0.07
    ãģ®ãģ¯
    0.07
    á»ķ
    0.07
    Activations Density 0.041%

    No Known Activations