© 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. 9181
    Prev
    Next
    INDEX
    Explanations

    requests for information

    np_max-act · gemini-2.0-flash

    The neuron activates on verbs and nouns associated with formally requesting or providing information—e.g. “report,” “details,” “provide,” “submit,” and “request.”

    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
     bee
    -0.08
    -provider
    -0.07
     Eyes
    -0.07
     citing
    -0.07
    ẻ
    -0.06
     prompt
    -0.06
     fundamentals
    -0.06
     role
    -0.06
     Price
    -0.06
     appointment
    -0.06
    POSITIVE LOGITS
     противоп
    0.07
     kvinder
    0.07
    nummer
    0.07
    ederland
    0.07
     Juventus
    0.07
     следующие
    0.07
    提高
    0.06
    altung
    0.06
    	INT
    0.06
    Projected
    0.06
    Activations Density 0.030%

    No Known Activations