© 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. 25227
    Prev
    Next
    INDEX
    Explanations

    communications provider

    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
     Shame
    -0.09
     Mouse
    -0.09
     Desire
    -0.09
    ung
    -0.08
    unk
    -0.08
     Tar
    -0.08
     Bark
    -0.08
    anted
    -0.08
    AMI
    -0.08
    331
    -0.08
    POSITIVE LOGITS
    ystack
    0.09
    stadt
    0.09
     subsystem
    0.09
    cdb
    0.09
    asaki
    0.09
    seealso
    0.09
    ãĥĩãĤ£ãĤ¢
    0.09
    Ľå»º
    0.09
    ovah
    0.08
    _SECURE
    0.08
    Activations Density 0.000%

    No Known Activations