© 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. 12057
    Prev
    Next
    INDEX
    Explanations

    hills and stillness

    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
    ed
    -0.14
    ìľ¼ë¡ľ
    -0.13
    est
    -0.12
    ex
    -0.12
    etic
    -0.11
    less
    -0.11
    eer
    -0.11
    essa
    -0.11
    ically
    -0.10
    off
    -0.10
    POSITIVE LOGITS
    inois
    0.20
    umin
    0.19
    llll
    0.19
    side
    0.18
    l
    0.18
    ls
    0.16
    ings
    0.16
    ory
    0.15
    inger
    0.15
    owy
    0.15
    Activations Density 0.057%

    No Known Activations