© 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 EvalsExportsinterp-engineNEWAPI 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. 79515
    Prev
    Next
    INDEX
    Explanations

    negation or conditional statements in code

    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
    Ŀ
    -0.07
    à¥įमà¤ķ
    -0.07
    mant
    -0.06
    uci
    -0.06
    -0.06
     UNU
    -0.06
    apse
    -0.06
    ä¸į足
    -0.06
    EventArgs
    -0.06
    å¥ı
    -0.06
    POSITIVE LOGITS
    yne
    0.07
    ìĤ¬íķŃ
    0.06
    eur
    0.06
    feof
    0.06
    Äįel
    0.06
    ching
    0.06
    ource
    0.06
     isNaN
    0.06
    bon
    0.06
    ards
    0.06
    Activations Density 0.012%

    No Known Activations