© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1814
    Prev
    Next
    INDEX
    Explanations

    subject, topic, or area

    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
    ambi
    -0.10
     Sentry
    -0.10
    Ymd
    -0.09
    [sizeof
    -0.09
    calar
    -0.09
    emmel
    -0.08
    DBC
    -0.08
    vail
    -0.08
    ê°ģ
    -0.08
     Wend
    -0.08
    POSITIVE LOGITS
     subject
    0.24
     fields
    0.21
     subjects
    0.20
     Subject
    0.19
     particular
    0.19
     sujet
    0.17
     area
    0.17
     field
    0.17
     topic
    0.17
     areas
    0.17
    Activations Density 0.138%

    No Known Activations