© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 42983
    Prev
    Next
    INDEX
    Explanations

    seeking lost answers

    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
    avery
    -0.09
    byss
    -0.09
    490
    -0.09
    CompleteListener
    -0.09
    нак
    -0.09
     Revel
    -0.08
     cáºŃn
    -0.08
    íħĶ
    -0.08
    nze
    -0.08
    DataExchange
    -0.08
    POSITIVE LOGITS
     answers
    0.29
     lost
    0.21
    answers
    0.21
     Answers
    0.21
     missing
    0.18
    Answers
    0.18
     meaning
    0.17
     answer
    0.16
    çŃĶæ¡Ī
    0.15
     ANSW
    0.15
    Activations Density 0.070%

    No Known Activations