© 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. 40455
    Prev
    Next
    INDEX
    Explanations

    "a" followed by adjective/noun

    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
    odore
    -0.13
    rias
    -0.11
    ct
    -0.11
    uter
    -0.11
    halb
    -0.11
    ppers
    -0.11
    riad
    -0.11
    ustralian
    -0.11
    pper
    -0.10
    UTO
    -0.10
    POSITIVE LOGITS
    parent
    0.13
    firm
    0.12
    tempt
    0.12
    HE
    0.12
     ll
    0.11
    eid
    0.11
    ft
    0.11
    ways
    0.11
    OV
    0.11
    db
    0.11
    Activations Density 0.091%

    No Known Activations