© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43042
    Prev
    Next
    INDEX
    Explanations

    there are several

    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
     tends
    -0.10
    sp
    -0.10
    InputGroup
    -0.09
     Kis
    -0.09
    yth
    -0.09
    might
    -0.09
     Feel
    -0.08
    ught
    -0.08
    did
    -0.08
     Kle
    -0.08
    POSITIVE LOGITS
     several
    0.22
     Several
    0.18
    Several
    0.17
    veral
    0.16
    åĩł
    0.14
     beberapa
    0.14
    åĩłä¸ª
    0.13
     plusieurs
    0.13
    หลาย
    0.13
     à¤ķà¤Ī
    0.12
    Activations Density 0.052%

    No Known Activations