© 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. 22197
    Prev
    Next
    INDEX
    Explanations

    normalize by row

    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
     motion
    -0.09
    abr
    -0.09
    olver
    -0.09
    RTOS
    -0.09
     pul
    -0.09
    nect
    -0.09
    _increment
    -0.09
     Baghd
    -0.09
    abbr
    -0.09
     Ulus
    -0.08
    POSITIVE LOGITS
     normalization
    0.24
     normalize
    0.23
     Normalize
    0.22
    normalize
    0.21
     scaling
    0.21
    .Normalize
    0.20
     norm
    0.20
     Norm
    0.20
     scale
    0.19
    å½Ĵ
    0.19
    Activations Density 0.049%

    No Known Activations