© 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. 43475
    Prev
    Next
    INDEX
    Explanations

    Pitata, python

    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
    oval
    -0.09
    ums
    -0.09
    hand
    -0.09
     Drum
    -0.09
    ermen
    -0.09
     Dover
    -0.09
     drum
    -0.09
     Brave
    -0.09
    245
    -0.09
    sd
    -0.09
    POSITIVE LOGITS
    bull
    0.18
    iful
    0.17
    sburgh
    0.16
    fall
    0.16
    amaha
    0.15
    falls
    0.14
     Pit
    0.14
    fork
    0.13
     pit
    0.13
    uit
    0.13
    Activations Density 0.036%

    No Known Activations