© 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. 9340
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects list-item markers (e.g. step numbers like “1.” or bullets) in procedural/instructional text.

    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
     बल
    -0.07
     instructed
    -0.07
    ैक
    -0.07
    irebase
    -0.06
    210
    -0.06
     至
    -0.06
    Structured
    -0.06
     allegations
    -0.06
     sebuah
    -0.06
     boon
    -0.06
    POSITIVE LOGITS
     BED
    0.07
     맛
    0.07
    .getD
    0.06
    وفي
    0.06
    romo
    0.06
    .nextDouble
    0.06
     Tig
    0.06
     staining
    0.06
     hostel
    0.06
    foil
    0.06
    Activations Density 0.084%

    No Known Activations