© 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. 124745
    Prev
    Next
    INDEX
    Explanations

    arts and writing

    np_max-act · gemini-2.0-flash

    The neuron activates on words describing artistic depiction—especially “portrayals” or similar terms indicating how a work represents a people, culture, or subject.

    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
     Fletcher
    -0.07
    姓
    -0.06
    iz
    -0.06
    ์ว
    -0.06
    ัต
    -0.06
     rupture
    -0.06
     دانشجوی
    -0.06
    .gf
    -0.06
    신
    -0.06
    ysa
    -0.06
    POSITIVE LOGITS
     música
    0.07
     cravings
    0.06
     Cash
    0.06
     FS
    0.06
    sn
    0.06
    _environment
    0.06
    -regexp
    0.06
     Xml
    0.06
     ag
    0.06
     أفضل
    0.06
    Activations Density 0.063%

    No Known Activations