© 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. 41135
    Prev
    Next
    INDEX
    Explanations

    cultural exchange

    np_max-act · gemini-2.0-flash

    discussions about the role and significance of religion in society.

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

    The neuron detects words and phrases about unity or common ground—particularly language around bridging or cutting through cultural or societal differences.

    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
     Rick
    -0.06
    AUTO
    -0.06
     Joey
    -0.06
    Rick
    -0.06
    signin
    -0.06
     후기
    -0.06
    717
    -0.05
     условия
    -0.05
     Constantin
    -0.05
    989
    -0.05
    POSITIVE LOGITS
    _GRID
    0.07
     g
    0.07
    -operative
    0.07
    .");↵
    0.07
    leans
    0.07
     आदम
    0.07
    %.↵
    0.07
    _PIX
    0.07
    /]
    0.06
    ∏
    0.06
    Activations Density 0.189%

    No Known Activations