© 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. 24722
    Prev
    Next
    INDEX
    Explanations

    introduction and overview

    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
     conferences
    -0.11
     seminars
    -0.10
    InBackground
    -0.10
     rehears
    -0.09
     Meetings
    -0.09
     Pars
    -0.09
     Transcript
    -0.09
     pars
    -0.09
     Lau
    -0.08
    æĦıè§ģ
    -0.08
    POSITIVE LOGITS
     break
    0.14
     followed
    0.14
     segment
    0.14
     ice
    0.13
     Q
    0.13
     discussion
    0.13
     introdu
    0.13
     breakout
    0.13
     introduction
    0.13
     Ice
    0.12
    Activations Density 0.074%

    No Known Activations