© 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
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38855
    Prev
    Next
    INDEX
    Explanations

    from us

    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
    isci
    -0.07
     afore
    -0.06
     architekt
    -0.06
    \OptionsResolver
    -0.06
    มà¸Ń
    -0.06
    imo
    -0.06
     relev
    -0.06
    &apos
    -0.06
     Atlas
    -0.06
    ãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢ
    -0.06
    POSITIVE LOGITS
    krv
    0.08
    .Formatter
    0.08
    InSection
    0.08
    ÐIJÑĢÑħÑĸв
    0.08
     %[
    0.07
     __("
    0.07
    ekil
    0.07
    ebek
    0.07
     strSql
    0.07
    eyse
    0.07
    Activations Density 0.066%

    No Known Activations