© 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. 60936
    Prev
    Next
    INDEX
    Explanations

    del paciente

    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
    ¶Į
    -0.10
    Â
    -0.09
    ÂĢÂĢ
    -0.09
    įng
    -0.09
    edback
    -0.09
    CISION
    -0.09
    hlas
    -0.09
    ì¸
    -0.08
    ertino
    -0.08
    Dlg
    -0.08
    POSITIVE LOGITS
    ews
    0.10
    /of
    0.10
    otos
    0.10
    l
    0.09
    /from
    0.09
    /to
    0.09
    Ê
    0.09
    lad
    0.09
     ifndef
    0.08
     Sung
    0.08
    Activations Density 0.055%

    No Known Activations