© 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. 55141
    Prev
    Next
    INDEX
    Explanations

    naturally occurring or newly permitted

    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
    istically
    -0.14
    ographically
    -0.12
    ised
    -0.12
    ially
    -0.11
    amente
    -0.11
    ably
    -0.11
    ized
    -0.11
    izzato
    -0.11
    aneously
    -0.11
    izable
    -0.10
    POSITIVE LOGITS
    rics
    0.20
    tics
    0.12
    mph
    0.12
    SelectedItem
    0.11
     mint
    0.11
     Yours
    0.11
    ãģ¦
    0.10
    yyyy
    0.10
    wed
    0.10
    udden
    0.10
    Activations Density 0.060%

    No Known Activations