© 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. 17972
    Prev
    Next
    INDEX
    Explanations

    phrases related to injury consequences and compensation

    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
    REET
    -0.08
    umas
    -0.07
    arkin
    -0.07
    cef
    -0.07
    jÃŃt
    -0.07
    ibre
    -0.07
    idon
    -0.07
     جÙħÙĩÙĪر
    -0.06
     dil
    -0.06
    ido
    -0.06
    POSITIVE LOGITS
     recovery
    0.07
     heal
    0.06
     healing
    0.06
     drain
    0.06
     recover
    0.06
     bills
    0.06
     medical
    0.06
    onda
    0.06
     Recovery
    0.06
    ammers
    0.06
    Activations Density 0.004%

    No Known Activations