© 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. 9125
    Prev
    Next
    INDEX
    Explanations

    Inability to think clearly

    np_max-act · gemini-2.0-flash

    The neuron fires on words and fragments that denote mental or cognitive states—thinking, consciousness, focus/​distract, hypnosis, suggestibility, drowsiness, etc.

    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
    恩
    -0.07
    undry
    -0.07
    Popover
    -0.07
     Stats
    -0.06
     Theater
    -0.06
    ('_
    -0.06
     Wenn
    -0.06
     auf
    -0.06
     Leisure
    -0.06
     meal
    -0.06
    POSITIVE LOGITS
    369
    0.07
    sequential
    0.06
     collaborated
    0.06
     picturesque
    0.06
     Hok
    0.06
     виб
    0.06
    ‌پدیا
    0.06
     dib
    0.06
    A
    0.06
     Exactly
    0.06
    Activations Density 0.013%

    No Known Activations