© 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. 73323
    Prev
    Next
    INDEX
    Explanations

    phrases related to burns and burn-related injuries

    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
    afia
    -0.07
    pike
    -0.06
     extras
    -0.06
    nero
    -0.06
    ertz
    -0.06
    -det
    -0.06
     deport
    -0.06
     extrad
    -0.06
    è´¹
    -0.06
    -found
    -0.06
    POSITIVE LOGITS
     burns
    0.13
     burn
    0.12
     Burns
    0.11
     Burn
    0.10
    Burn
    0.10
    burn
    0.10
     skin
    0.10
     burned
    0.10
    skin
    0.09
    Skin
    0.09
    Activations Density 0.010%

    No Known Activations