© 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. 45058
    Prev
    Next
    INDEX
    Explanations

    cause stutter or distortion

    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
     shades
    -0.11
    onical
    -0.10
     blurred
    -0.10
     blurry
    -0.10
     Arb
    -0.09
     Pir
    -0.09
    abyrin
    -0.09
    ashi
    -0.09
    FORMAT
    -0.09
     Shades
    -0.09
    POSITIVE LOGITS
     artifacts
    0.31
     arte
    0.27
     artifact
    0.26
     alias
    0.22
    artifact
    0.22
    Artifact
    0.20
     Artifact
    0.20
     Gibbs
    0.17
    alias
    0.17
     Arte
    0.17
    Activations Density 0.093%

    No Known Activations