© 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. 12510
    Prev
    Next
    INDEX
    Explanations

    like this / so

    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
    conti
    -0.10
    edic
    -0.10
    ãģĦãĤĭ
    -0.09
    edes
    -0.09
    âĢ¢\n\n
    -0.09
     Karma
    -0.08
    inka
    -0.08
    ullet
    -0.08
    èĮĤ
    -0.08
    akov
    -0.08
    POSITIVE LOGITS
     follows
    0.19
    -wise
    0.18
    ewise
    0.17
     below
    0.17
     so
    0.16
    è¿Ļæł·
    0.16
     váºŃy
    0.16
    wise
    0.16
    WISE
    0.15
    å¦Ĥä¸ĭ
    0.15
    Activations Density 0.018%

    No Known Activations