© 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. 44947
    Prev
    Next
    INDEX
    Explanations

    Parentheses/brackets

    np_max-act · gemini-2.0-flash

    This neuron activates on descriptive modifiers—especially adjectives that qualify formats, styles, or categories (e.g. “digital,” “electronic,” “classic,” “fiscal”).

    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
    財
    -0.07
    .live
    -0.06
    -graph
    -0.06
    SOFTWARE
    -0.06
     TURN
    -0.06
     STAR
    -0.06
     kdyby
    -0.06
     Friedman
    -0.06
    (',',$
    -0.06
     tolik
    -0.06
    POSITIVE LOGITS
     Inject
    0.07
    licable
    0.07
     Purple
    0.06
    (QWidget
    0.06
     prow
    0.06
     applicable
    0.06
     shutil
    0.06
    �
    0.06
     Tone
    0.06
     incidents
    0.06
    Activations Density 0.024%

    No Known Activations