© 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. 1795
    Prev
    Next
    INDEX
    Explanations

    code line numbers

    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
    eum
    -0.10
     Richt
    -0.09
     conven
    -0.09
    midt
    -0.09
    //{{
    -0.09
    avra
    -0.09
    INLINE
    -0.09
    idot
    -0.08
     afford
    -0.08
    ::.
    -0.08
    POSITIVE LOGITS
    è¡Į
    0.11
     col
    0.09
     è¡Į
    0.09
     Pride
    0.09
    onaut
    0.09
    ë²Ī째
    0.09
    ilan
    0.08
     Quartz
    0.08
     Lamb
    0.08
    쪽
    0.08
    Activations Density 0.043%

    No Known Activations