© 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. 36370
    Prev
    Next
    INDEX
    Explanations

    us coin/har/coli/se/uf/che/ION/ammen

    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
    es
    -0.13
    h
    -0.12
    hack
    -0.11
    hos
    -0.11
    ew
    -0.11
    ty
    -0.11
    t
    -0.11
    em
    -0.11
    ton
    -0.11
    hot
    -0.10
    POSITIVE LOGITS
    ser
    0.14
    iasm
    0.14
    à¥įतà¤ķ
    0.13
     Operand
    0.13
    cular
    0.13
    lararası
    0.13
    UARIO
    0.13
    oidal
    0.13
    anne
    0.12
    INESS
    0.12
    Activations Density 0.092%

    No Known Activations