© 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. 4551
    Prev
    Next
    INDEX
    Explanations

    processes, products, methods, results

    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
     however
    -0.16
     totiž
    -0.13
     sice
    -0.12
     jednak
    -0.10
     jedoch
    -0.10
    Å¡ak
    -0.09
     Jaw
    -0.09
    <|begin_of_text|>
    -0.09
     же
    -0.09
     Hlav
    -0.09
    POSITIVE LOGITS
     serta
    0.11
    348
    0.10
    aved
    0.09
    pt
    0.09
    469
    0.09
    arks
    0.09
    adera
    0.09
    aves
    0.09
    ewe
    0.08
    ãģĿãģĵ
    0.08
    Activations Density 0.175%

    No Known Activations