© 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. 29150
    Prev
    Next
    INDEX
    Explanations

    identifying likenesses

    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
    -only
    -0.10
     Tos
    -0.09
    ãģıãĤĵ
    -0.09
    873
    -0.09
    imd
    -0.09
    XHR
    -0.09
     Rever
    -0.09
    887
    -0.08
    uls
    -0.08
    -exclusive
    -0.08
    POSITIVE LOGITS
    -like
    0.64
    like
    0.47
    -style
    0.38
    -esque
    0.37
    -type
    0.35
    LIKE
    0.30
    _like
    0.29
    èĪ¬
    0.26
     style
    0.25
    style
    0.24
    Activations Density 0.412%

    No Known Activations