© 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. 44572
    Prev
    Next
    INDEX
    Explanations

    ì¤ followed by ĺ

    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
     ëĦ¤ìĿ´íĬ¸
    -0.12
    ãĥ»ãĥ»ãĥ»\n\n
    -0.10
    oops
    -0.10
    .nz
    -0.09
    adge
    -0.09
    _ISR
    -0.09
     ë¸
    -0.09
    timezone
    -0.09
    .Apis
    -0.09
    iosper
    -0.09
    POSITIVE LOGITS
    Į
    0.11
    igo
    0.10
    į
    0.10
     cred
    0.09
    ĺ
    0.09
    asp
    0.09
    orget
    0.09
    ong
    0.09
     perfect
    0.09
     Thanks
    0.09
    Activations Density 0.012%

    No Known Activations