© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108826
    Prev
    Next
    INDEX
    Explanations

    communities

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of a “community” designation (singular or plural) in geographic/place descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to unincorporated communities in Indiana.

    oai_token-act-pair · gpt-4o-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
    ipelines
    -0.07
     fatt
    -0.07
     adults
    -0.07
    igious
    -0.07
    ultipart
    -0.06
    ラス
    -0.06
    овах
    -0.06
     فوت
    -0.06
     repaint
    -0.06
    thers
    -0.06
    POSITIVE LOGITS
    .Provider
    0.06
    <float
    0.06
     weaknesses
    0.06
     foram
    0.06
    γορ
    0.06
     сол
    0.06
    ''"
    0.06
     cultivation
    0.05
     Dram
    0.05
    (error
    0.05
    Activations Density 0.001%

    No Known Activations