© 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. 21991
    Prev
    Next
    INDEX
    Explanations

    file path definition

    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
     Rhe
    -0.10
    abin
    -0.10
    FilePath
    -0.10
    _paths
    -0.10
     pathetic
    -0.09
    FullPath
    -0.08
    _FILENO
    -0.08
    WithPath
    -0.08
    utral
    -0.08
    ally
    -0.08
    POSITIVE LOGITS
    ways
    0.15
    finding
    0.14
    way
    0.14
    etically
    0.13
    ogen
    0.13
    names
    0.13
    ForResource
    0.13
    finder
    0.12
    ologies
    0.12
    /to
    0.12
    Activations Density 0.020%

    No Known Activations