© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 34855
    Prev
    Next
    INDEX
    Explanations

    history and its impact

    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
    ingham
    -0.10
    ì¦Į
    -0.09
     -*-č\n
    -0.08
     univers
    -0.08
    826
    -0.08
    lint
    -0.08
     åĵģ
    -0.08
     ÏĥÏħμβ
    -0.08
    oomla
    -0.08
    ByKey
    -0.08
    POSITIVE LOGITS
     history
    0.31
    history
    0.23
     History
    0.22
     identity
    0.20
     politics
    0.19
    History
    0.19
     HISTORY
    0.18
     иÑģÑĤоÑĢии
    0.18
    _history
    0.18
     culture
    0.18
    Activations Density 0.060%

    No Known Activations