© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121616
    Prev
    Next
    INDEX
    Explanations

    expressions of personal struggle or defiance against authority and societal expectations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Text segments that contain or set up expressions of negative judgment, refusal, or statements about what is deemed unacceptable or impermissible in a particular context.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    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
    Negative Logits
     hải
    -0.06
     Duck
    -0.06
    568
    -0.06
    vil
    -0.06
    veis
    -0.06
     Beaver
    -0.06
    alez
    -0.06
    itchens
    -0.06
    hausen
    -0.06
    ÃŃses
    -0.05
    POSITIVE LOGITS
     unacceptable
    0.15
     intoler
    0.10
     refuse
    0.09
     intolerance
    0.09
     acceptable
    0.09
     refusal
    0.09
     refused
    0.08
    acceptable
    0.08
     Absolutely
    0.08
    oser
    0.08
    Activations Density 0.056%

    No Known Activations