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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 41928
    Prev
    Next
    INDEX
    Explanations

    application interaction

    np_max-act · gemini-2.0-flash

    The neuron fires for verbs that describe interacting with a user interface—things like click, toggle, view, move, scroll, 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
    oders
    -0.07
     spoof
    -0.06
    ewart
    -0.06
    ometer
    -0.06
    Sink
    -0.06
     Siemens
    -0.06
    Serial
    -0.06
    otes
    -0.06
    ive
    -0.06
    皮
    -0.06
    POSITIVE LOGITS
     forControlEvents
    0.06
    <TEntity
    0.06
     adec
    0.06
     chances
    0.06
     شع
    0.06
    (change
    0.06
    .bid
    0.06
    �
    0.06
     каче
    0.06
     territorial
    0.06
    Activations Density 0.076%

    No Known Activations