© 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. 29295
    Prev
    Next
    INDEX
    Explanations

    requirement for this situation

    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
     Ir
    -0.11
    opt
    -0.10
     Pocket
    -0.10
     abandoned
    -0.10
     optimal
    -0.10
     pocket
    -0.10
    HP
    -0.09
    adro
    -0.09
     Pepsi
    -0.09
    DIM
    -0.09
    POSITIVE LOGITS
     Safety
    0.19
     safety
    0.19
     SIL
    0.15
    Safety
    0.15
    afety
    0.13
     design
    0.13
    è¾
    0.11
     designers
    0.11
     accident
    0.11
    fail
    0.11
    Activations Density 0.100%

    No Known Activations