© 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. 110241
    Prev
    Next
    INDEX
    Explanations

    ou

    np_max-act · gemini-2.0-flash

    The neuron fires on formal Czech honorific expressions (e.g. “velikou ctí” “with great honor”) used in polite or ceremonial addresses.

    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
     cruel
    -0.07
    ascript
    -0.07
    λλά
    -0.07
     dvou
    -0.07
    ασίας
    -0.07
     adjacent
    -0.07
    Annotations
    -0.07
    aju
    -0.06
    ingly
    -0.06
    SETS
    -0.06
    POSITIVE LOGITS
    +++
    0.06
    .pat
    0.06
    .ModelSerializer
    0.06
    _SUB
    0.06
    Ζ
    0.06
    概
    0.05
    _die
    0.05
     сход
    0.05
     '=',
    0.05
     여성
    0.05
    Activations Density 0.059%

    No Known Activations