© 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. 62793
    Prev
    Next
    INDEX
    Explanations

    DNA sequence and polymerase

    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
    ias
    -0.13
     Ping
    -0.10
    pons
    -0.10
     ping
    -0.09
    ĥ½
    -0.09
    annie
    -0.09
    etine
    -0.09
     ï½°
    -0.09
    oni
    -0.09
    MainFrame
    -0.09
    POSITIVE LOGITS
    /pro
    0.14
     Damage
    0.13
    zym
    0.13
    /R
    0.12
    ase
    0.11
    JB
    0.11
     meth
    0.11
    emia
    0.11
     metab
    0.11
    issance
    0.10
    Activations Density 0.014%

    No Known Activations