© 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. 19932
    Prev
    Next
    INDEX
    Explanations

    possessive followed by 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
    anza
    -0.10
    own
    -0.10
    èĩªå·±
    -0.10
    uby
    -0.10
     surroundings
    -0.08
    åĹ
    -0.08
    isay
    -0.08
    idy
    -0.08
    TRIES
    -0.08
     Simpson
    -0.08
    POSITIVE LOGITS
     behalf
    0.21
    /my
    0.12
     exact
    0.11
     stuff
    0.10
     stead
    0.10
    stuff
    0.10
    ãĤĪãģĨãģª
    0.10
     footsteps
    0.10
    neath
    0.10
     praises
    0.10
    Activations Density 0.117%

    No Known Activations