© 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. 31991
    Prev
    Next
    INDEX
    Explanations

    map related to views, markers, directories

    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
    <Entry
    -0.13
    Maps
    -0.12
    _maps
    -0.11
    erb
    -0.11
    esser
    -0.11
    Mappings
    -0.11
    Map
    -0.10
     mapped
    -0.10
    aries
    -0.10
    Mapped
    -0.10
    POSITIVE LOGITS
    pping
    0.26
    illary
    0.19
    pped
    0.18
    reduce
    0.18
    Reduce
    0.15
    uto
    0.15
    les
    0.15
    StateToProps
    0.15
    nik
    0.14
    (&:
    0.14
    Activations Density 0.024%

    No Known Activations