© 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. 41368
    Prev
    Next
    INDEX
    Explanations

    being identified or described

    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
    otec
    -0.10
     Lloyd
    -0.10
    utor
    -0.09
     tieten
    -0.09
    847
    -0.09
    еди
    -0.09
    Unhandled
    -0.09
     spelling
    -0.09
     å¼
    -0.08
    loo
    -0.08
    POSITIVE LOGITS
     represented
    0.14
     mentioned
    0.13
    represented
    0.13
     profile
    0.12
     whose
    0.12
     Sands
    0.10
     chronic
    0.10
     reflected
    0.10
     described
    0.10
    azu
    0.10
    Activations Density 0.194%

    No Known Activations