© 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. 78254
    Prev
    Next
    INDEX
    Explanations

    references to quantum physics concepts and parameters

    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
     Trouble
    -0.06
    elman
    -0.06
    _tE
    -0.06
     appearances
    -0.06
    inkel
    -0.06
    inkle
    -0.06
     answer
    -0.06
    Trou
    -0.06
    osg
    -0.06
    ëĭµ
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.10
    essler
    0.07
     moderate
    0.07
     thêm
    0.07
    áli
    0.07
    ène
    0.07
     spo
    0.07
    bedo
    0.06
     external
    0.06
     applied
    0.06
    Activations Density 0.060%

    No Known Activations