© 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. 63836
    Prev
    Next
    INDEX
    Explanations

    star or stars

    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
    ãģĬãĤĬ
    -0.13
    ense
    -0.11
    ãģĦãģ¾ãģĻ
    -0.10
    lices
    -0.10
    isper
    -0.10
    going
    -0.10
    edl
    -0.09
    nal
    -0.09
     Shel
    -0.09
    دارÛĮ
    -0.09
    POSITIVE LOGITS
    ved
    0.21
    light
    0.21
    kest
    0.19
    let
    0.18
    ry
    0.17
    vation
    0.17
    burst
    0.16
    lets
    0.16
    彡
    0.16
    ling
    0.16
    Activations Density 0.022%

    No Known Activations