© 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. 45192
    Prev
    Next
    INDEX
    Explanations

    large scale or quantity

    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
     enlarged
    -0.12
     tiny
    -0.11
    iminal
    -0.10
    lic
    -0.09
    /ay
    -0.09
     (<
    -0.09
     small
    -0.09
    ORK
    -0.09
     little
    -0.09
    daq
    -0.09
    POSITIVE LOGITS
    -scale
    0.37
     scale
    0.21
     enough
    0.20
    scale
    0.20
    -format
    0.19
    Scale
    0.18
     Scale
    0.18
    (r
    0.18
    cale
    0.17
     intestine
    0.16
    Activations Density 0.049%

    No Known Activations