© 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. 837
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens related to accessing external web resources (e.g. links, internet, fetch).

    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
    ?option
    -0.07
    _sigma
    -0.07
    zac
    -0.06
    getModel
    -0.06
    ela
    -0.06
     pervasive
    -0.06
     وذلك
    -0.06
     Bair
    -0.06
     être
    -0.06
     Jung
    -0.06
    POSITIVE LOGITS
     نظری
    0.07
     utilizar
    0.07
    	logging
    0.06
     Sản
    0.06
     nguyện
    0.06
     výro
    0.06
    .defaults
    0.06
    (template
    0.06
     timestamps
    0.06
     sản
    0.06
    Activations Density 0.001%

    No Known Activations