© 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. 23050
    Prev
    Next
    INDEX
    Explanations

    I am here, designed or trained

    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
     fetisch
    -0.09
    /forms
    -0.09
     ragaz
    -0.09
     ÑĢекомендÑĥ
    -0.08
    bdb
    -0.08
    ero
    -0.08
    esa
    -0.08
     scales
    -0.08
     ***!\n
    -0.08
    ITS
    -0.08
    POSITIVE LOGITS
     designed
    0.18
     training
    0.18
    training
    0.13
     Training
    0.13
    è®Ń
    0.13
     trained
    0.13
     learning
    0.12
     обÑĥÑĩ
    0.12
     Designed
    0.12
     myself
    0.12
    Activations Density 0.203%

    No Known Activations