© 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. 30895
    Prev
    Next
    INDEX
    Explanations

    prices, tuition, description; respective

    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
    .Formatter
    -0.09
    ida
    -0.09
     mole
    -0.08
    CORD
    -0.08
    orian
    -0.08
    zen
    -0.08
    Ľå»º
    -0.08
    rone
    -0.07
     intermedi
    -0.07
    oshi
    -0.07
    POSITIVE LOGITS
     respective
    0.20
     each
    0.20
     Each
    0.15
     respectively
    0.15
     corresponding
    0.15
    each
    0.14
     ÙĦÙĥÙĦ
    0.13
    Each
    0.13
     their
    0.12
     EACH
    0.12
    Activations Density 0.400%

    No Known Activations