© 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. 22283
    Prev
    Next
    INDEX
    Explanations

    les poitevins, Châteauneuf

    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
     Harr
    -0.10
     French
    -0.09
    vore
    -0.09
     bore
    -0.09
     french
    -0.09
    ãĥķãĥ¬
    -0.09
     Afro
    -0.09
     jung
    -0.08
     HLS
    -0.08
     Alger
    -0.08
    POSITIVE LOGITS
     Po
    0.13
     Saud
    0.13
     po
    0.10
     Tanner
    0.10
    abb
    0.10
     Isle
    0.10
     Genç
    0.10
     clos
    0.10
    Po
    0.10
     Eve
    0.09
    Activations Density 0.016%

    No Known Activations