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

    Neuronpedia

    Jacobian LensNEW
    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. 38303
    Prev
    Next
    INDEX
    Explanations

    hand

    np_max-act · gemini-2.0-flash

    This neuron activates on hyphenated “first-hand” references, marking mentions of direct, firsthand experiences or observations.

    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
    ("/
    -0.06
     kosher
    -0.06
    TouchListener
    -0.06
     lParam
    -0.06
    .COM
    -0.06
     unlock
    -0.06
     الان
    -0.06
    اقع
    -0.06
     array
    -0.06
    -con
    -0.06
    POSITIVE LOGITS
     eyewitness
    0.07
    pořád
    0.06
     conting
    0.06
     авг
    0.06
     ◎
    0.06
     Northwest
    0.06
     náz
    0.06
     очевид
    0.06
     Cf
    0.06
     Such
    0.06
    Activations Density 0.028%

    No Known Activations