© 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. 41048
    Prev
    Next
    INDEX
    Explanations

    Lind

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases related to factual consistency and verification (e.g., “factually,” “consistent,” “confirm,” “consistent with”).

    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
     races
    -0.06
    ULATOR
    -0.06
     THEORY
    -0.06
    models
    -0.06
     JS
    -0.06
    -sector
    -0.06
     А
    -0.06
    ož
    -0.06
     commodities
    -0.06
     coaches
    -0.06
    POSITIVE LOGITS
    ！↵↵↵↵
    0.07
    ozřejmě
    0.07
    _LARGE
    0.06
    +j
    0.06
     паци
    0.06
    /lgpl
    0.06
     당시
    0.06
     견
    0.06
     domaine
    0.06
    ємо
    0.06
    Activations Density 0.001%

    No Known Activations