© 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. 36709
    Prev
    Next
    INDEX
    Explanations

    previous or preceding numbers/terms

    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
    以åIJİ
    -0.13
     originally
    -0.12
    uj
    -0.11
     successors
    -0.11
     NotImplemented
    -0.10
     originals
    -0.10
     Originally
    -0.10
     newer
    -0.10
     postfix
    -0.10
    aura
    -0.10
    POSITIVE LOGITS
     previous
    0.41
    previous
    0.33
    Previous
    0.32
     Previous
    0.32
    .previous
    0.26
     prev
    0.25
    (previous
    0.24
     prior
    0.23
    _previous
    0.23
    åīį
    0.23
    Activations Density 0.130%

    No Known Activations