© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7801
    Prev
    Next
    INDEX
    Explanations

    frequent

    np_max-act · gemini-2.0-flash

    The neuron fires on the components of common adjective–noun compound phrases (e.g. “frequent flyer points,” “security system”).

    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
    .TH
    -0.07
     preceding
    -0.06
     roofs
    -0.06
    zig
    -0.06
     thường
    -0.06
    mqtt
    -0.06
    SCRIPTOR
    -0.06
    uai
    -0.06
    quare
    -0.06
     cafe
    -0.06
    POSITIVE LOGITS
    对象
    0.07
     курс
    0.06
     imshow
    0.06
    血
    0.06
    _padding
    0.06
     NTN
    0.06
     الطبي
    0.06
    .repositories
    0.06
    .onNext
    0.06
     Sử
    0.06
    Activations Density 0.296%

    No Known Activations