© 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. 110364
    Prev
    Next
    INDEX
    Explanations

    replacement

    np_max-act · gemini-2.0-flash

    This neuron detects phrasing that introduces how a material is used or its function (“for,” “in,” “as” in contexts like “replacement for,” “used in,” or “as a”).

    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
     آماده
    -0.07
     Politics
    -0.07
    VALID
    -0.06
     COMMIT
    -0.06
     Username
    -0.06
    開発
    -0.06
    	update
    -0.06
    give
    -0.06
    xpath
    -0.06
    Haz
    -0.06
    POSITIVE LOGITS
    -rating
    0.07
     GeForce
    0.07
    нд
    0.07
     České
    0.07
     substantial
    0.06
     rodents
    0.06
     discredit
    0.06
    ор
    0.06
     фактор
    0.06
    (dtype
    0.06
    Activations Density 0.023%

    No Known Activations