© 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. 42822
    Prev
    Next
    INDEX
    Explanations

    positioning and fixing

    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
    _demo
    -0.10
    éĭ
    -0.09
     selectively
    -0.09
    ï½ŀï½ŀ
    -0.09
     ìľłíĺķ
    -0.08
    _baseline
    -0.08
    ãĢ
    -0.08
     attachments
    -0.08
     decl
    -0.08
     torch
    -0.08
    POSITIVE LOGITS
     ï½Į
    0.11
     prelim
    0.11
     integr
    0.11
    âī§
    0.10
     wir
    0.10
     Beetle
    0.10
     filmy
    0.10
     Portions
    0.09
    ugin
    0.09
    .theta
    0.09
    Activations Density 0.037%

    No Known Activations