© 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. 9672
    Prev
    Next
    INDEX
    Explanations

    technical data contexts

    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
    _data
    -0.15
    Source
    -0.12
    (s
    -0.12
    _dataset
    -0.12
    SourceType
    -0.11
    DataSource
    -0.11
    Data
    -0.11
    DataFrame
    -0.11
    pre
    -0.11
    _DATA
    -0.10
    POSITIVE LOGITS
    ils
    0.22
    stream
    0.16
    :image
    0.15
    streams
    0.14
    Sets
    0.14
    cube
    0.14
    iled
    0.13
    store
    0.13
    项
    0.13
    ë²ł
    0.13
    Activations Density 0.070%

    No Known Activations