© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33702
    Prev
    Next
    INDEX
    Explanations

    delving deeper into

    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
     ÑħÑĥд
    -0.11
    anford
    -0.09
    .IsNullOr
    -0.09
    358
    -0.09
    Ħĸ
    -0.09
    prech
    -0.09
    .scala
    -0.09
    etections
    -0.09
     artificially
    -0.09
    umlu
    -0.09
    POSITIVE LOGITS
     into
    0.35
     vÃło
    0.25
    Into
    0.24
    into
    0.24
     Into
    0.22
     INTO
    0.21
     deep
    0.20
    _into
    0.20
    .into
    0.17
    æ·±
    0.15
    Activations Density 0.039%

    No Known Activations