© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 127008
    Prev
    Next
    INDEX
    Explanations

    Music/Celebrity discussions

    np_max-act · gemini-2.0-flash

    The neuron responds to high-frequency English function words—especially auxiliary and linking verbs (forms of “be,” “have,” “is,” “to”) that structure declarative prose.

    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
     Bannon
    -0.07
     Ents
    -0.07
     samen
    -0.07
     bộ
    -0.07
     movable
    -0.07
    으로
    -0.06
     números
    -0.06
     hdr
    -0.06
     Kota
    -0.06
    lı
    -0.06
    POSITIVE LOGITS
     �
    0.07
    (Collider
    0.06
    śmy
    0.06
     nebyla
    0.06
    AxisSize
    0.06
    MySQL
    0.06
    NAMESPACE
    0.06
    surf
    0.06
    -holder
    0.05
     researching
    0.05
    Activations Density 0.063%

    No Known Activations