© 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. 17-LLAMASCOPE-RES-131K
    11. 3102
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface layout and styling in programming 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
    ofile
    -0.07
    rve
    -0.06
    ÑĸйÑģ
    -0.06
     ún
    -0.06
    hel
    -0.06
    _PR
    -0.06
    à¥įरस
    -0.06
    osit
    -0.06
    enia
    -0.06
    spb
    -0.06
    POSITIVE LOGITS
    _except
    0.07
    estruct
    0.07
    uchos
    0.06
     proportion
    0.06
    ieval
    0.06
    997
    0.06
    arity
    0.06
    modal
    0.06
     Cel
    0.06
     devotion
    0.06
    Activations Density 0.001%

    No Known Activations