© 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. 59212
    Prev
    Next
    INDEX
    Explanations

    a unique person or thing

    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
    _OVERFLOW
    -0.08
    WithMany
    -0.08
     unrelated
    -0.08
     varying
    -0.08
     fine
    -0.08
     Excell
    -0.08
    _abort
    -0.08
     Separate
    -0.08
    ÙĪÛĮÙĩ
    -0.08
     sudden
    -0.08
    POSITIVE LOGITS
     unique
    0.64
    unique
    0.55
     Unique
    0.50
    Unique
    0.50
     special
    0.46
    çī¹æ®Ĭ
    0.46
     uniqueness
    0.45
     unusual
    0.44
    _unique
    0.44
     UNIQUE
    0.44
    Activations Density 0.387%

    No Known Activations