© 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. 25237
    Prev
    Next
    INDEX
    Explanations

    stay at, in, up, with, inside

    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
     outr
    -0.09
    vla
    -0.09
     sustained
    -0.09
    ucene
    -0.09
    nze
    -0.09
    etur
    -0.09
     Vict
    -0.09
    .positions
    -0.09
    iento
    -0.08
     Wesley
    -0.08
    POSITIVE LOGITS
     longer
    0.32
     Longer
    0.25
     longest
    0.16
     stay
    0.14
     till
    0.12
    cation
    0.12
     lâu
    0.12
     Till
    0.11
     until
    0.11
     anonymous
    0.10
    Activations Density 0.046%

    No Known Activations