© 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. 16924
    Prev
    Next
    INDEX
    Explanations

    but as word start

    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
     alas
    -0.13
     Bew
    -0.10
    IEL
    -0.10
    ÙĨز
    -0.10
    stime
    -0.09
    iв
    -0.09
    gid
    -0.09
    nze
    -0.09
    635
    -0.09
    ALES
    -0.09
    POSITIVE LOGITS
    ters
    0.24
    ler
    0.23
    ts
    0.20
    term
    0.20
    ting
    0.20
    ressed
    0.19
    ÑģÑıÑĤ
    0.18
    ted
    0.18
    ane
    0.17
    ch
    0.17
    Activations Density 0.049%

    No Known Activations