© 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. 39983
    Prev
    Next
    INDEX
    Explanations

    themes of denial and blindness to societal issues

    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
     rodin
    -0.08
    æ³Ĭ
    -0.07
    ázd
    -0.07
    dech
    -0.07
    íĻľ
    -0.07
    ymm
    -0.07
    ë
    -0.07
    _canvas
    -0.07
    åIJIJ
    -0.07
    ymous
    -0.07
    POSITIVE LOGITS
     denial
    0.13
     blindness
    0.10
     blind
    0.09
     Den
    0.08
     deny
    0.08
     ignorance
    0.08
     ignore
    0.08
     until
    0.08
    -ignore
    0.08
     blinds
    0.08
    Activations Density 0.045%

    No Known Activations