© 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. 51374
    Prev
    Next
    INDEX
    Explanations

    Electro, Euro, Petro prefixes followed by related suffixes

    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
    un
    -0.13
    ro
    -0.13
    us
    -0.12
    mos
    -0.12
    r
    -0.11
    l
    -0.11
    ros
    -0.10
    ul
    -0.10
    mo
    -0.10
    p
    -0.10
    POSITIVE LOGITS
    chemical
    0.13
    scopic
    0.12
    logy
    0.12
    amazon
    0.11
    dynamic
    0.11
    american
    0.11
    aug
    0.11
    typed
    0.11
    active
    0.10
    ’;nun
    0.10
    Activations Density 0.069%

    No Known Activations