© 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. 17414
    Prev
    Next
    INDEX
    Explanations

    technique, method, style, or treatment

    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
    724
    -0.10
    .mousePosition
    -0.10
    ´:
    -0.09
    @js
    -0.08
     огÑĢа
    -0.08
     Gest
    -0.08
    ernel
    -0.08
    151
    -0.08
    ó
    -0.08
    abor
    -0.08
    POSITIVE LOGITS
     technique
    0.29
     method
    0.27
     type
    0.25
     form
    0.24
     mode
    0.22
     forms
    0.22
     Technique
    0.19
     genre
    0.19
    method
    0.19
     branch
    0.19
    Activations Density 0.195%

    No Known Activations