© 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. 15678
    Prev
    Next
    INDEX
    Explanations

    Isso / Esto seguido por explicação

    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
     поба
    -0.14
    /***/
    -0.09
    yd
    -0.09
     dabei
    -0.09
    ken
    -0.09
    ulen
    -0.09
    center
    -0.08
    ces
    -0.08
    ÏĥÏĢ
    -0.08
    adel
    -0.08
    POSITIVE LOGITS
     happened
    0.11
    utom
    0.10
     último
    0.10
     latter
    0.10
    houette
    0.10
     means
    0.10
    æĦıåij³
    0.09
    ãĤīãģ®
    0.09
     Spotlight
    0.09
     happens
    0.09
    Activations Density 0.030%

    No Known Activations