© 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. 54527
    Prev
    Next
    INDEX
    Explanations

    who / he / soldiers died

    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
    ivec
    -0.09
     enduring
    -0.09
     truncate
    -0.08
     Fried
    -0.08
    orian
    -0.08
     cancers
    -0.08
    369
    -0.08
     dq
    -0.08
    hape
    -0.08
     DMA
    -0.08
    POSITIVE LOGITS
     died
    0.49
     dies
    0.46
     die
    0.43
     dying
    0.38
    die
    0.35
     Dies
    0.34
     Died
    0.34
    æŃ»
    0.33
     DIE
    0.31
    _die
    0.29
    Activations Density 0.080%

    No Known Activations