© 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. 13195
    Prev
    Next
    INDEX
    Explanations

    explosions or sudden events

    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
     fro
    -0.10
     OMG
    -0.10
     Rue
    -0.09
    _HERSHEY
    -0.09
    733
    -0.09
     MDB
    -0.09
     Mall
    -0.09
    YP
    -0.09
     puls
    -0.09
    rage
    -0.09
    POSITIVE LOGITS
     Bang
    0.37
     boom
    0.37
     bang
    0.35
     Boom
    0.32
    Bang
    0.30
    bang
    0.29
    Boom
    0.28
    boom
    0.28
     BO
    0.26
     Bam
    0.23
    Activations Density 0.119%

    No Known Activations