© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89326
    Prev
    Next
    INDEX
    Explanations

    Technology

    np_max-act · gemini-2.0-flash

    The neuron responds to pronouns and linking verbs (e.g. “It,” “They,” “are,” “is”)—i.e. common function words that introduce or connect explanatory statements.

    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
    형
    -0.06
    inox
    -0.06
    لوب
    -0.06
    丹
    -0.06
    ANJI
    -0.06
    ekim
    -0.06
    โท
    -0.06
    clientId
    -0.06
    Attrib
    -0.06
    unik
    -0.06
    POSITIVE LOGITS
    -controller
    0.07
    zes
    0.07
    (states
    0.07
     moments
    0.07
    ographed
    0.06
     checking
    0.06
     Ν
    0.06
     dě
    0.06
     UserController
    0.06
    ukt
    0.06
    Activations Density 0.033%

    No Known Activations