© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45157
    Prev
    Next
    INDEX
    Explanations

    axis and dimension

    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
     Mach
    -0.11
    rex
    -0.11
    raquo
    -0.10
    :.:.:.:.:
    -0.10
     Sez
    -0.09
     Wade
    -0.09
    adr
    -0.09
    lier
    -0.09
    adro
    -0.09
    mach
    -0.09
    POSITIVE LOGITS
     axis
    0.35
     dimension
    0.29
    axis
    0.29
     direction
    0.24
     Axis
    0.24
    Axis
    0.23
    (axis
    0.23
     Dimension
    0.22
     axes
    0.22
    -axis
    0.22
    Activations Density 0.054%

    No Known Activations