© 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. 129953
    Prev
    Next
    INDEX
    Explanations

    You

    np_max-act · gemini-2.0-flash

    This neuron detects the numbered workout‐routine headline (“8 No‐Equipment HIIT Moves You Can Do in 30 Seconds”), i.e. titles that list a specific number of fitness moves with an imperative call to action.

    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
     normalization
    -0.07
    dy
    -0.07
     객체
    -0.07
     noise
    -0.06
    _width
    -0.06
     liste
    -0.06
     noir
    -0.06
     рек
    -0.06
    няти
    -0.06
     타이
    -0.06
    POSITIVE LOGITS
    CREATE
    0.06
     Aub
    0.06
     몸
    0.06
    omedical
    0.06
    _RESULTS
    0.06
    _CSS
    0.06
    subnet
    0.06
    .AutoScaleMode
    0.06
     NDEBUG
    0.06
    픽
    0.06
    Activations Density 0.101%

    No Known Activations