© 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. 36254
    Prev
    Next
    INDEX
    Explanations

    product category followed by group/scope

    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
    ertools
    -0.09
    SFML
    -0.08
    olly
    -0.08
    ChildIndex
    -0.08
    muz
    -0.08
    porno
    -0.08
    ursal
    -0.08
    æĢ§çļĦ
    -0.08
    ุม
    -0.08
    id
    -0.08
    POSITIVE LOGITS
     pool
    0.17
     base
    0.13
     profile
    0.13
    base
    0.13
     palette
    0.12
     matrix
    0.12
    pool
    0.12
     network
    0.11
     structure
    0.11
     list
    0.10
    Activations Density 0.144%

    No Known Activations