© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 389
    Prev
    Next
    INDEX
    Explanations

    Pa followed by 'pe', 'll', 'ís', 'esi', 'quete'

    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
    zet
    -0.10
    ba
    -0.10
    ber
    -0.09
     pant
    -0.09
    pi
    -0.09
    bla
    -0.09
    ille
    -0.09
    encion
    -0.09
    ails
    -0.08
    ochen
    -0.08
    POSITIVE LOGITS
    ired
    0.12
     pa
    0.11
    ience
    0.11
    Pa
    0.11
     Pa
    0.10
    uly
    0.10
    UL
    0.10
    istani
    0.10
    ÅĦst
    0.10
     па
    0.10
    Activations Density 0.028%

    No Known Activations