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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73725
    Prev
    Next
    INDEX
    Explanations

    Parenthetical clauses

    np_max-act · gemini-2.0-flash

    requests for flexibility in working hours.

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

    This neuron detects formal or business-style phrasing—polite connectors and sophisticated vocabulary used in professional email writing.

    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
    ',

↵
    -0.07
     factors
    -0.06
    GREEN
    -0.06
    �
    -0.06
    гов
    -0.06
    woo
    -0.06
    (Schedulers
    -0.06
     BOTTOM
    -0.06
    ши
    -0.06
    PEC
    -0.06
    POSITIVE LOGITS
    ціональ
    0.07
     filesize
    0.07
     Innovative
    0.07
    .");
    0.06
     MM
    0.06
     жінок
    0.06
    .Alert
    0.06
     раді
    0.06
     western
    0.06
     Ionic
    0.06
    Activations Density 0.262%

    No Known Activations