© 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. 31052
    Prev
    Next
    INDEX
    Explanations

    absoluteness

    np_max-act · gemini-2.0-flash

    technical jargon and questions related to programming and development practices.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron strongly activates on words conveying totality or absolutes (e.g. “always,” “everything”).

    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
     yolc
    -0.06
     Greece
    -0.06
     definite
    -0.06
    (JSONObject
    -0.06
    ستم
    -0.06
     Palestinians
    -0.06
     talk
    -0.06
     ritual
    -0.06
    	tmp
    -0.06
     paper
    -0.06
    POSITIVE LOGITS
     //_
    0.07
    TEE
    0.07
     IK
    0.07
     наш
    0.07
     усл
    0.06
    aspberry
    0.06
    <E
    0.06
    vented
    0.06
    <Game
    0.06
     evolves
    0.06
    Activations Density 0.149%

    No Known Activations