© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 11678
    Prev
    Next
    INDEX
    Explanations

    here's or here are

    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
    ers
    -0.09
    lef
    -0.09
    amber
    -0.09
    ane
    -0.09
    disconnect
    -0.08
    986
    -0.08
    amed
    -0.08
    able
    -0.08
    áb
    -0.08
    -paper
    -0.08
    POSITIVE LOGITS
    ¶Į
    0.11
    below
    0.11
    ãĥ¼ãĤ¹
    0.09
    ford
    0.09
    ina
    0.09
    after
    0.09
    rire
    0.09
    çek
    0.09
    cura
    0.09
    546
    0.08
    Activations Density 0.059%

    No Known Activations