© 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. 43246
    Prev
    Next
    INDEX
    Explanations

    time and self-reflection

    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
    isObject
    -0.08
     aforementioned
    -0.07
     afore
    -0.07
    .wx
    -0.07
    åľŃ
    -0.07
    bersome
    -0.07
    ych
    -0.07
    à¸Ĺย
    -0.07
    fragistics
    -0.07
    .mvp
    -0.07
    POSITIVE LOGITS
    instanc
    0.10
     %[
    0.10
    Ìģt
    0.08
    #ac
    0.08
     coquine
    0.08
    andest
    0.08
    Lorem
    0.08
    ebek
    0.07
     salopes
    0.07
    ãĤ
    0.07
    Activations Density 0.014%

    No Known Activations