© 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. 44570
    Prev
    Next
    INDEX
    Explanations

    <|start_header_id|>

    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
    Í
    -0.09
    .MixedReality
    -0.09
    .GraphicsUnit
    -0.09
    ColumnsMode
    -0.08
    ÑĢож
    -0.08
    WithMany
    -0.08
    ToLower
    -0.08
     ï½ľ
    -0.07
     Toro
    -0.07
    ï¾IJ
    -0.07
    POSITIVE LOGITS
    _REF
    0.09
    วล
    0.08
    setw
    0.08
    âĶĥ
    0.08
    atre
    0.08
    odore
    0.08
     بÙĪابة
    0.07
    ^K
    0.07
     \'
    0.07
    oku
    0.07
    Activations Density 0.075%

    No Known Activations