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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30848
    Prev
    Next
    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of technology/innovation-related terms.

    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
     عق
    -0.07
    .RESULT
    -0.06
    wo
    -0.06
     films
    -0.06
     издел
    -0.06
    im
    -0.06
     immersed
    -0.06
    odě
    -0.06
     finishing
    -0.06
    .version
    -0.06
    POSITIVE LOGITS
     aesthetic
    0.07
    .Up
    0.06
    	Field
    0.06
    urchased
    0.06
     tqdm
    0.06
    hetic
    0.06
     Paige
    0.06
     практически
    0.06
     airborne
    0.06
     Суд
    0.06
    Activations Density 0.026%

    No Known Activations