© 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. 27576
    Prev
    Next
    INDEX
    Explanations

    verb infinitives ending sentences

    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
    .Byte
    -0.09
    ently
    -0.09
    ĸī
    -0.09
    ibly
    -0.08
     Barnett
    -0.08
     octave
    -0.08
    ningen
    -0.08
    ÅĻeh
    -0.08
    еÑĢами
    -0.08
    VERY
    -0.08
    POSITIVE LOGITS
    án
    0.20
    á
    0.18
    ÃŃa
    0.16
    bbe
    0.16
    anno
    0.15
    ão
    0.15
    emos
    0.14
    ás
    0.13
     will
    0.12
    Ãł
    0.12
    Activations Density 0.051%

    No Known Activations