© 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. 44118
    Prev
    Next
    INDEX
    Explanations

    his he her s/he his/her

    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
    /Dk
    -0.10
    âĶ´
    -0.09
    ê¸Ķ
    -0.09
    ĺIJ
    -0.08
     ë¸
    -0.08
    í
    -0.08
     Momentum
    -0.08
    unkt
    -0.08
    atro
    -0.08
    ëł
    -0.08
    POSITIVE LOGITS
    /her
    0.38
    /she
    0.30
    her
    0.23
    .her
    0.21
    /-
    0.17
    ï¼ı
    0.17
    /
    0.16
    /a
    0.16
    HER
    0.16
    (a
    0.15
    Activations Density 0.208%

    No Known Activations