Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 91503
    Prev
    Next
    INDEX
    Explanations

    Recognizing something when seen

    np_max-act · gemini-2.0-flash

    This neuron detects subjective “I … when I …” recognition or judgment phrases (e.g. “I know a great company when I see one”).

    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
    Tower
    -0.06
    ryption
    -0.06
     Dro
    -0.06
    Martin
    -0.06
    agnar
    -0.06
    填
    -0.06
     Channel
    -0.06
     black
    -0.06
    Thomas
    -0.06
     combating
    -0.06
    POSITIVE LOGITS
    \e
    0.07
     виступ
    0.07
     Scene
    0.06
     berk
    0.06
     eth
    0.06
    _bo
    0.06
    عات
    0.06
     İŞ
    0.06
    回来
    0.06
     dispozici
    0.06
    Activations Density 0.048%

    No Known Activations