© 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. 12466
    Prev
    Next
    INDEX
    Explanations

    SQL statement hints

    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
     Campos
    -0.10
     Stan
    -0.10
     dilation
    -0.09
     Kata
    -0.09
     consort
    -0.09
     Stanford
    -0.09
     Dün
    -0.08
    ãĢĢ
    -0.08
    chor
    -0.08
     Cousins
    -0.08
    POSITIVE LOGITS
     Inn
    0.16
     inn
    0.14
    noDB
    0.11
    inn
    0.11
    .ib
    0.11
    _rwlock
    0.11
    _frm
    0.10
     PSI
    0.10
    .isNullOrEmpty
    0.10
     mys
    0.10
    Activations Density 0.014%

    No Known Activations