© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 26321
    Prev
    Next
    INDEX
    Explanations

    is defensive or feels fear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    овеÑĢ
    -0.10
     hes
    -0.09
    ainty
    -0.09
     tort
    -0.09
    SFML
    -0.09
     Tort
    -0.09
     politely
    -0.09
     cred
    -0.09
    aho
    -0.08
    atched
    -0.08
    POSITIVE LOGITS
     contr
    0.19
     defense
    0.16
     defensive
    0.16
     defend
    0.16
     defence
    0.16
     remorse
    0.15
     savun
    0.15
     guilty
    0.14
     sheep
    0.14
     defended
    0.14
    Activations Density 0.049%

    No Known Activations