© 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. 23858
    Prev
    Next
    INDEX
    Explanations

    dispositivo de detección of Ruby, 50% of temperatures

    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
    addir
    -0.09
    acomment
    -0.08
     konkrét
    -0.07
    ÐĬ
    -0.07
    NullException
    -0.07
    -INF
    -0.07
    ÂĢÂĢ
    -0.07
    <|begin_of_text|>
    -0.07
    působ
    -0.07
    _vlog
    -0.07
    POSITIVE LOGITS
    (always
    0.07
    stride
    0.07
    (Optional
    0.07
     à¸ģรà¸ģ
    0.06
    ãĢijãĢIJ
    0.06
    StateException
    0.06
    olley
    0.06
    -
    0.06
    /m
    0.06
    /in
    0.06
    Activations Density 0.350%

    No Known Activations