© 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. 1540
    Prev
    Next
    INDEX
    Explanations

    examples starting with "an e-"

    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
     bike
    -0.12
     bicy
    -0.11
     biking
    -0.10
     cyclists
    -0.10
     racket
    -0.09
     bikes
    -0.09
     bicycle
    -0.09
     exerc
    -0.09
     vehicle
    -0.09
     alo
    -0.09
    POSITIVE LOGITS
     casual
    0.14
     general
    0.13
    cas
    0.12
     Casual
    0.11
     recre
    0.11
     serious
    0.11
    general
    0.10
     eskort
    0.10
     causal
    0.10
    Cas
    0.10
    Activations Density 0.093%

    No Known Activations