© 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. 30406
    Prev
    Next
    INDEX
    Explanations

    technical code/text

    np_max-act · gemini-2.0-flash

    The neuron responds to descriptive words for physical appearance, especially color adjectives and other trait descriptors.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    finds named entities and identifiers (proper names, locations, dates/invoice numbers and other numeric or label-like tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     rotating
    -0.07
    ॉप
    -0.07
    ccd
    -0.07
     lø
    -0.07
    убли
    -0.06
    Disp
    -0.06
    اسة
    -0.06
    	AM
    -0.06
     Moh
    -0.06
    Moh
    -0.06
    POSITIVE LOGITS
    $s
    0.07
     района
    0.07
     ail
    0.06
     янва
    0.06
     Conexion
    0.06
    Enumerable
    0.06
    ああ
    0.06
    "){
↵
    0.06
    )";↵↵
    0.06
    £
    0.06
    Activations Density 0.730%

    No Known Activations