Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 69068
    Prev
    Next
    INDEX
    Explanations

    code questions

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of an “article” (especially in contexts like “newspaper article,” “article mentioned,” 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
     ayar
    -0.07
    円
    -0.06
     Edwin
    -0.06
    andal
    -0.06
     findBy
    -0.06
    icare
    -0.06
    (nil
    -0.06
    NewItem
    -0.06
    asal
    -0.06
    Toggle
    -0.06
    POSITIVE LOGITS
     detr
    0.07
    _Long
    0.06
     sublist
    0.06
     Tort
    0.06
     Nad
    0.06
    ۲۰۲
    0.06
     vlas
    0.06
    腾
    0.06
    methodPointerType
    0.06
     Sergei
    0.06
    Activations Density 0.089%

    No Known Activations