© 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. 61016
    Prev
    Next
    INDEX
    Explanations

    science fiction novels and authors

    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
    rieve
    -0.10
     Ultra
    -0.10
     Baz
    -0.09
    rap
    -0.09
     Hybrid
    -0.09
     Ninja
    -0.09
     Uns
    -0.09
     Elephant
    -0.09
    flix
    -0.09
     fou
    -0.08
    POSITIVE LOGITS
     science
    0.32
     Science
    0.29
     SF
    0.28
     sf
    0.26
    SF
    0.25
    Science
    0.24
    science
    0.23
     sci
    0.21
    sf
    0.21
     Sci
    0.20
    Activations Density 0.119%

    No Known Activations