© 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. 7570
    Prev
    Next
    INDEX
    Explanations

    underscore

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on runs of non‐alphanumeric characters forming ASCII art or diagram‐style “drawing” blocks (e.g. repeated pipes, slashes, underscores, etc.).

    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
    Stat
    -0.07
     faculties
    -0.07
    matter
    -0.07
     Mitchell
    -0.07
     Baz
    -0.07
     subsection
    -0.07
    -market
    -0.07
    .one
    -0.07
    قه
    -0.07
    alty
    -0.07
    POSITIVE LOGITS
     __("
    0.07
     キャ
    0.06
    (tool
    0.06
     πολι
    0.06
     bağlantı
    0.06
     odor
    0.06
     uplifting
    0.06
     оскільки
    0.06
     الاجتماع
    0.06
     isteyen
    0.06
    Activations Density 0.005%

    No Known Activations