© 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. 36390
    Prev
    Next
    INDEX
    Explanations

    be classified or described

    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
     nicknamed
    -0.10
    iname
    -0.09
     subdivisions
    -0.09
     sanki
    -0.09
     Conj
    -0.09
     subdivision
    -0.09
    ktop
    -0.09
     Named
    -0.09
    882
    -0.08
     Known
    -0.08
    POSITIVE LOGITS
     label
    0.21
    æłĩ
    0.20
     mark
    0.20
     oznaÄį
    0.19
     marked
    0.19
     declared
    0.18
    label
    0.18
    .label
    0.17
     class
    0.16
     marks
    0.16
    Activations Density 0.183%

    No Known Activations