© 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 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. 71277
    Prev
    Next
    INDEX
    Explanations

    declarative statements or quotes related to legal proceedings

    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
    ansi
    -0.08
    haar
    -0.07
    .hwp
    -0.06
     UNU
    -0.06
    odial
    -0.06
    enstein
    -0.06
    pell
    -0.06
     reprint
    -0.06
    leck
    -0.06
    obo
    -0.06
    POSITIVE LOGITS
    aravel
    0.07
     usted
    0.07
    Mr
    0.07
     Crown
    0.06
     Mr
    0.06
    Monitor
    0.06
    gam
    0.06
     Your
    0.06
     crown
    0.06
    Your
    0.06
    Activations Density 0.001%

    No Known Activations