© 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. 13059
    Prev
    Next
    INDEX
    Explanations

    -select

    np_max-act · gemini-2.0-flash

    This neuron fires on vendor-prefixed CSS property names (e.g. “-webkit-user-select”, “-moz-user-select”, “-ms-touch-action,” 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
     Ning
    -0.07
     forwarded
    -0.07
     trivial
    -0.06
    	back
    -0.06
    -even
    -0.06
    .Drawable
    -0.06
     LogManager
    -0.06
     PHY
    -0.06
    072
    -0.06
    cü
    -0.06
    POSITIVE LOGITS
     specification
    0.07
    Remarks
    0.07
    nem
    0.07
    ocs
    0.06
    .constants
    0.06
     ill
    0.06
     totiž
    0.06
    गल
    0.06
     uży
    0.06
    αρά
    0.06
    Activations Density 0.000%

    No Known Activations