© 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. 36820
    Prev
    Next
    INDEX
    Explanations

    anc or unc prefixes

    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
    l
    -0.14
    on
    -0.14
    o
    -0.13
    onom
    -0.13
    lv
    -0.12
    ont
    -0.12
    om
    -0.12
    omy
    -0.12
    lin
    -0.11
    ono
    -0.11
    POSITIVE LOGITS
    ̧
    0.13
    rist
    0.13
    illary
    0.12
    CESS
    0.12
    HECK
    0.11
    LEAR
    0.11
    ipated
    0.10
    ients
    0.10
    ules
    0.10
    eor
    0.10
    Activations Density 0.044%

    No Known Activations