© 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. 109830
    Prev
    Next
    INDEX
    Explanations

    disabled or selected

    np_max-act · gemini-2.0-flash

    The neuron fires whenever the text refers to disabling a UI element (e.g. the “disabled” attribute or property).

    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
     Continent
    -0.08
    แผน
    -0.07
     Tea
    -0.06
     Find
    -0.06
    ymm
    -0.06
     bonds
    -0.06
     Approach
    -0.06
     Seas
    -0.06
    bin
    -0.06
     leftist
    -0.06
    POSITIVE LOGITS
     :";↵
    0.08
    _folders
    0.07
    :::::::::::::::
    0.06
     CLOSED
    0.06
    iring
    0.06
    िग
    0.06
     RemoteException
    0.06
    zew
    0.06
     chức
    0.06
     podcast
    0.06
    Activations Density 0.002%

    No Known Activations