© 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. 55837
    Prev
    Next
    INDEX
    Explanations

    this one is a bit of a

    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
    rlen
    -0.09
     pÅĻece
    -0.09
     enim
    -0.09
    OULD
    -0.09
    ihan
    -0.09
    бÑĥдÑĮ
    -0.09
    ngx
    -0.09
    CEED
    -0.09
    ungan
    -0.08
    NotFoundError
    -0.08
    POSITIVE LOGITS
     sounds
    0.45
     Sounds
    0.38
    Sounds
    0.37
    sounds
    0.36
     sound
    0.29
     sounded
    0.26
     sounding
    0.25
     may
    0.22
     might
    0.22
    Sound
    0.21
    Activations Density 0.134%

    No Known Activations