© 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. 124697
    Prev
    Next
    INDEX
    Explanations

    Research studies

    np_max-act · gemini-2.0-flash

    The neuron detects methodological framing or objective statements in scientific writing—phrases signaling study aims or procedures (e.g. “In order to…,” “We investigated…,” “Using this method…”).

    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
     anal
    -0.07
     arteries
    -0.06
     ainda
    -0.06
     emojis
    -0.06
    зв
    -0.06
    detalle
    -0.06
    ulado
    -0.06
    童
    -0.06
    etu
    -0.06
    rating
    -0.06
    POSITIVE LOGITS
    =[],
    0.06
    $img
    0.06
    .what
    0.06
     Blessed
    0.06
     getHeight
    0.06
     Крас
    0.06
     trotz
    0.06
     Как
    0.06
    (hist
    0.06
    .AppendLine
    0.06
    Activations Density 0.056%

    No Known Activations