© 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. 41651
    Prev
    Next
    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash

    This neuron detects definitional or listing cues—words like “composed of,” “including,” “excludes,” and “encompass” that introduce or delimit a group’s membership or components.

    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
    认识
    -0.07
     LEDs
    -0.07
     Trends
    -0.07
     制
    -0.06
     flows
    -0.06
     LED
    -0.06
     четвер
    -0.06
    imating
    -0.06
    .te
    -0.06
    .Root
    -0.06
    POSITIVE LOGITS
     registrazione
    0.06
    /register
    0.06
     investigations
    0.06
     nghiệ
    0.06
    .history
    0.06
     sonucunda
    0.06
    vek
    0.06
    SingleOrDefault
    0.05
     Cah
    0.05
    ™
    0.05
    Activations Density 0.036%

    No Known Activations