© 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. 4871
    Prev
    Next
    INDEX
    Explanations

    terms associated with evaluation and grading systems

    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
    ixer
    -0.07
    iec
    -0.06
    adius
    -0.06
    ë£
    -0.06
    ello
    -0.06
    ,#
    -0.06
     ÄIJá»ĭnh
    -0.06
     sur
    -0.05
    äºķ
    -0.05
    ibrary
    -0.05
    POSITIVE LOGITS
     letter
    0.07
    Ñĭп
    0.07
    hec
    0.07
    ertos
    0.07
     Feedback
    0.07
    flate
    0.06
    flation
    0.06
    اÙģ
    0.06
     distribution
    0.06
     Cru
    0.06
    Activations Density 0.002%

    No Known Activations