© 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. 105760
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and accountability related to accidents

    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
    å½±
    -0.06
    idel
    -0.06
     Holt
    -0.06
    uchs
    -0.06
     Vogue
    -0.06
     Jed
    -0.06
    filtro
    -0.06
    alg
    -0.06
    iti
    -0.06
     Sorting
    -0.06
    POSITIVE LOGITS
     Safety
    0.11
     safety
    0.11
    Safety
    0.10
     unsafe
    0.10
     accident
    0.10
    afety
    0.10
     Accident
    0.09
     Unsafe
    0.08
     accidents
    0.08
     crash
    0.08
    Activations Density 0.008%

    No Known Activations