© 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. 19675
    Prev
    Next
    INDEX
    Explanations

    and heavy, breeze whispers, birds sing

    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
    •GENERAL

    No Comments

    Negative Logits
     Caucas
    -0.11
     totally
    -0.10
     infer
    -0.10
    vably
    -0.10
     Controls
    -0.09
    viously
    -0.09
     wur
    -0.09
     controls
    -0.08
     ethnic
    -0.08
     slim
    -0.08
    POSITIVE LOGITS
     god
    0.12
     fucks
    0.10
    god
    0.10
     tentative
    0.09
     crater
    0.09
     swell
    0.09
     supp
    0.09
     Renders
    0.09
     handjob
    0.09
    assen
    0.08
    Activations Density 0.244%

    No Known Activations