© 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. 36053
    Prev
    Next
    INDEX
    Explanations

    ere / gere / Pere / cere / prere

    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
    re
    -0.20
    so
    -0.18
    sh
    -0.17
    rec
    -0.16
    ss
    -0.15
    ra
    -0.15
    set
    -0.15
    ser
    -0.15
    ri
    -0.14
    sets
    -0.14
    POSITIVE LOGITS
    ignty
    0.12
    otypical
    0.11
    otypes
    0.11
    gow
    0.11
    bral
    0.11
    ference
    0.10
    hog
    0.10
    psilon
    0.10
    azÄĥ
    0.10
    álu
    0.10
    Activations Density 0.074%

    No Known Activations