© 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. 44646
    Prev
    Next
    INDEX
    Explanations

    when followed by words

    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
    ----</
    -0.09
    ulan
    -0.09
    AndPassword
    -0.09
     jadx
    -0.09
    \tTokenName
    -0.09
    âĻ¡
    -0.08
    %č\n
    -0.08
    наÑģлÑĸд
    -0.08
    .Fat
    -0.08
    ÂĢÂĢ
    -0.08
    POSITIVE LOGITS
     If
    0.09
     When
    0.09
    å¦Ĥæŀľ
    0.08
    对äºİ
    0.08
    When
    0.08
    If
    0.08
     maneuver
    0.08
     EÄŁer
    0.08
    uno
    0.08
    _metric
    0.08
    Activations Density 0.062%

    No Known Activations