© 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. 18185
    Prev
    Next
    INDEX
    Explanations

    which may

    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
     shorthand
    -0.11
     detriment
    -0.10
    791
    -0.10
    oren
    -0.09
     writ
    -0.09
    undra
    -0.09
    911
    -0.09
    peat
    -0.09
    aji
    -0.09
     accompl
    -0.08
    POSITIVE LOGITS
     cat
    0.16
     fetch
    0.12
     club
    0.12
     major
    0.12
     bag
    0.11
     Cat
    0.11
    shall
    0.11
     fetched
    0.10
    fetch
    0.10
     shall
    0.10
    Activations Density 0.227%

    No Known Activations