© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41536
    Prev
    Next
    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash

    This neuron fires on the opening parenthesis of photo or media‐credit asides (e.g. “(AFP/Getty Images)”).

    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
     brave
    -0.07
     insp
    -0.07
    からない
    -0.06
    (bus
    -0.06
    ких
    -0.06
    στό
    -0.06
     انتقال
    -0.06
    vement
    -0.06
    ifold
    -0.06
     Paypal
    -0.06
    POSITIVE LOGITS
    .Vector
    0.07
    Viewer
    0.06
    )'
    0.06
    ansi
    0.06
    َ
    0.06
    \\"
    0.06
    :x
    0.06
    ська
    0.06
    块
    0.06
    *x
    0.06
    Activations Density 0.010%

    No Known Activations