© 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. 18416
    Prev
    Next
    INDEX
    Explanations

    types of

    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
     possibilities
    -0.09
    reesome
    -0.09
     Genre
    -0.08
    utsch
    -0.08
     surroundings
    -0.08
    fragistics
    -0.08
    ripp
    -0.08
     complexities
    -0.08
     whole
    -0.08
    Constants
    -0.08
    POSITIVE LOGITS
     types
    0.37
     kinds
    0.35
     type
    0.26
    types
    0.24
     kind
    0.24
     sorts
    0.23
     TYPES
    0.21
    -types
    0.20
     Types
    0.19
    ç±»åŀĭ
    0.17
    Activations Density 0.129%

    No Known Activations