© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109873
    Prev
    Next
    INDEX
    Explanations

    processes and relationships

    np_max-act · gemini-2.0-flash

    This neuron responds to tokens that contain a doubled character (e.g. “passes,” “focussed,” “follow”).

    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
     تشخیص
    -0.07
    arb
    -0.07
    選
    -0.06
    جوی
    -0.06
    _sample
    -0.06
    602
    -0.06
    OA
    -0.06
    окс
    -0.06
     walnut
    -0.06
     Approval
    -0.06
    POSITIVE LOGITS
    크기
    0.06
    .prototype
    0.06
     revisit
    0.06
    rarian
    0.06
    /setup
    0.06
    plete
    0.06
     نادي
    0.06
     siblings
    0.06
    atron
    0.05
    人物
    0.05
    Activations Density 0.227%

    No Known Activations