© 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. 60551
    Prev
    Next
    INDEX
    Explanations

    how to do it

    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
     metic
    -0.09
    839
    -0.09
     handled
    -0.09
    ramer
    -0.09
    ellas
    -0.09
    _UNS
    -0.08
    ány
    -0.08
     nic
    -0.08
     Kurd
    -0.08
    _preference
    -0.08
    POSITIVE LOGITS
     technique
    0.23
     techniques
    0.21
     Technique
    0.19
     taught
    0.17
     performed
    0.16
     Techniques
    0.16
    æĬĢ
    0.16
     teach
    0.15
     moves
    0.13
     sequences
    0.13
    Activations Density 0.164%

    No Known Activations