© 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. 50862
    Prev
    Next
    INDEX
    Explanations

    there 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
    abee
    -0.09
    kening
    -0.09
    odesk
    -0.08
    ảnh
    -0.08
    adu
    -0.08
    ellery
    -0.08
     ÙĨدارد
    -0.08
    åĿĤ
    -0.08
    ERO
    -0.07
    igion
    -0.07
    POSITIVE LOGITS
     there
    0.61
     There
    0.49
    There
    0.47
    there
    0.47
     ÙĩÙĨاÙĥ
    0.39
     THERE
    0.37
     theres
    0.26
     еÑģÑĤÑĮ
    0.25
    .There
    0.24
     där
    0.23
    Activations Density 0.244%

    No Known Activations