© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 792
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron fires on sequence tokens that look like alphanumeric identifiers (e.g. codes, claim or patient numbers, IDs).

    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
    ルド
    -0.07
     favored
    -0.07
    Backend
    -0.07
    �
    -0.07
    guild
    -0.07
     furnace
    -0.06
     echo
    -0.06
    /cc
    -0.06
     Truck
    -0.06
     Εθν
    -0.06
    POSITIVE LOGITS
    -too
    0.06
     him
    0.06
     입
    0.06
     jeder
    0.06
    фици
    0.06
     стад
    0.06
     أق
    0.06
    想到
    0.06
     shri
    0.05
     ребенка
    0.05
    Activations Density 0.207%

    No Known Activations