© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 40997
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens in date/time metadata (e.g. year, month, day, timestamps) within HTML documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setters
    -0.07
    members
    -0.07
    랜드
    -0.07
     doc
    -0.06
     Connor
    -0.06
     EnumerableStream
    -0.06
     Diğer
    -0.06
     matchup
    -0.06
    Chance
    -0.06
     йому
    -0.06
    POSITIVE LOGITS
    .junit
    0.07
    fiber
    0.06
    .setColor
    0.06
     lif
    0.06
     Obesity
    0.06
    vertices
    0.06
    环境
    0.06
     pf
    0.06
     Kontakt
    0.06
     influx
    0.06
    Activations Density 0.001%

    No Known Activations