© 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. 9-LLAMASCOPE-RES-131K
    11. 99286
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts, efforts, or actions taken to disrupt or violate rules

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ulton
    -0.08
    ÐŁÐļ
    -0.07
    ÑĢава
    -0.07
    avana
    -0.07
    iform
    -0.07
    ķ
    -0.07
    xfff
    -0.06
    folio
    -0.06
    ory
    -0.06
    tap
    -0.06
    POSITIVE LOGITS
    kke
    0.06
     COPYRIGHT
    0.06
    stav
    0.06
    ulin
    0.06
    _attempt
    0.06
     Lens
    0.05
    steller
    0.05
    andom
    0.05
    _iterator
    0.05
    owitz
    0.05
    Activations Density 0.023%

    No Known Activations