© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13401
    Prev
    Next
    INDEX
    Explanations

    amazon.com

    np_max-act · gemini-2.0-flash

    The neuron activates on Amazon product link tokens (e.g., “.amazon” or “.com” in Amazon URLs).

    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
     zaměř
    -0.07
     nods
    -0.07
    폴
    -0.06
    _pop
    -0.06
    .pan
    -0.06
    }"
    -0.06
    019
    -0.06
     گرف
    -0.06
    razione
    -0.06
    logging
    -0.06
    POSITIVE LOGITS
    .amazon
    0.10
     Amazon
    0.07
    _dem
    0.06
     ファ
    0.06
             
    0.06
     HOH
    0.06
    _basename
    0.06
    asctime
    0.06
    (QWidget
    0.06
    _TAGS
    0.06
    Activations Density 0.001%

    No Known Activations