© 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. 61457
    Prev
    Next
    INDEX
    Explanations

    elements related to accessibility and inclusion, particularly for marginalized groups

    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
    antan
    -0.09
    _locals
    -0.08
    cheme
    -0.08
    pga
    -0.07
    iç
    -0.07
    lass
    -0.07
    ingroup
    -0.07
    aim
    -0.07
    /compiler
    -0.07
    uyá»ĩn
    -0.07
    POSITIVE LOGITS
     whose
    0.09
    ACCESS
    0.07
     who
    0.07
     rural
    0.07
     access
    0.07
    áh
    0.07
     may
    0.07
     unable
    0.06
     might
    0.06
     simply
    0.06
    Activations Density 0.028%

    No Known Activations