© 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. 29514
    Prev
    Next
    INDEX
    Explanations

    assistant <|end_header_id|>

    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
     cru
    -0.09
     CO
    -0.09
    --[[
    -0.09
     Jerry
    -0.09
    alu
    -0.09
     beh
    -0.09
    209
    -0.08
     EX
    -0.08
     ACCESS
    -0.08
     Pac
    -0.08
    POSITIVE LOGITS
     Cheat
    0.10
    plr
    0.09
     Willi
    0.09
    å¿
    0.09
    witter
    0.09
    obl
    0.09
    ington
    0.08
    sian
    0.08
    aec
    0.08
    constitutional
    0.08
    Activations Density 0.053%

    No Known Activations