© 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. 2281
    Prev
    Next
    INDEX
    Explanations

    delete

    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
    ness
    -0.10
    abi
    -0.10
    eller
    -0.09
    stri
    -0.09
    -up
    -0.09
    rup
    -0.08
    rát
    -0.08
    emann
    -0.08
    ayas
    -0.08
    ordan
    -0.08
    POSITIVE LOGITS
    (delete
    0.14
    æİī
    0.13
    beat
    0.11
     bá»ı
    0.11
    (del
    0.11
    ions
    0.10
     khá»ıi
    0.10
     Deletes
    0.10
    ion
    0.10
    CriticalSection
    0.10
    Activations Density 0.021%

    No Known Activations