© 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. 20797
    Prev
    Next
    INDEX
    Explanations

    expressing apparent states or perceptions

    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
     emin
    -0.11
    ï½ľ
    -0.11
    andr
    -0.10
    isser
    -0.10
    umba
    -0.10
    .Dependency
    -0.10
    adies
    -0.09
    ãģĬãĤĬ
    -0.09
    owell
    -0.09
     easily
    -0.08
    POSITIVE LOGITS
    ingly
    0.20
    lessly
    0.18
    (ed
    0.13
     να
    0.13
    antly
    0.12
     to
    0.12
    ings
    0.12
    ily
    0.12
    ingga
    0.11
    ly
    0.11
    Activations Density 0.014%

    No Known Activations