© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 11385
    Prev
    Next
    INDEX
    Explanations

    finding the answer

    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
    Negative Logits
    Ap
    -0.08
     Dum
    -0.08
    avigator
    -0.08
    oken
    -0.08
    670
    -0.08
     Apartment
    -0.08
     ancestral
    -0.08
    ucha
    -0.08
    aldi
    -0.08
     Scratch
    -0.08
    POSITIVE LOGITS
     answer
    0.48
    answer
    0.39
    çŃĶæ¡Ī
    0.35
     answers
    0.35
     ans
    0.34
     Answer
    0.32
    Answer
    0.31
    ANS
    0.30
     answered
    0.29
     оÑĤвеÑĤ
    0.29
    Activations Density 0.430%

    No Known Activations