© 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. 40133
    Prev
    Next
    INDEX
    Explanations

    dynamic or variable

    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
     Passive
    -0.10
     statically
    -0.09
     passive
    -0.09
     recursively
    -0.09
    aida
    -0.08
    ãĢĢl
    -0.08
    andalone
    -0.08
     Stand
    -0.08
    aur
    -0.08
    imas
    -0.08
    POSITIVE LOGITS
     dynamic
    0.46
     Dynamic
    0.38
    dynamic
    0.36
    Dynamic
    0.33
     dynam
    0.33
     variable
    0.33
    _dynamic
    0.32
    åĬ¨
    0.31
    .dynamic
    0.30
    _DYNAMIC
    0.29
    Activations Density 0.227%

    No Known Activations