© 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. 62586
    Prev
    Next
    INDEX
    Explanations

    residential lane or tall buildings

    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
    ICAST
    -0.10
     Cone
    -0.10
     Mant
    -0.10
    iras
    -0.09
    arrass
    -0.09
     quot
    -0.09
    ullet
    -0.09
     Terrace
    -0.09
     perpetual
    -0.09
     Latitude
    -0.09
    POSITIVE LOGITS
    amen
    0.18
     amen
    0.18
    .os
    0.13
     osm
    0.12
    (OS
    0.12
     пÑĢид
    0.12
     os
    0.11
    jos
    0.11
     ways
    0.11
     residential
    0.11
    Activations Density 0.022%

    No Known Activations