© 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. 107718
    Prev
    Next
    INDEX
    Explanations

    discussions related to allegations of misconduct and injury incidents

    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
    ensi
    -0.07
    umont
    -0.06
    дина
    -0.06
     demokrat
    -0.06
    _fence
    -0.06
    .iter
    -0.06
    fund
    -0.06
     slu
    -0.06
    ÙĤÛĮ
    -0.06
    abler
    -0.06
    POSITIVE LOGITS
     involving
    0.09
     category
    0.08
     reported
    0.08
    verbs
    0.08
     cases
    0.07
    Report
    0.07
     report
    0.07
     ë°ľìĥĿ
    0.07
    ernel
    0.07
    reported
    0.07
    Activations Density 0.011%

    No Known Activations