© 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. 92256
    Prev
    Next
    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of light sources or lighting descriptions.

    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
     Maurice
    -0.07
    стин
    -0.07
    lerdir
    -0.07
    用的
    -0.06
     SES
    -0.06
     prostřed
    -0.06
    산
    -0.06
    池
    -0.06
     秋
    -0.06
    rn
    -0.06
    POSITIVE LOGITS
    ादन
    0.07
     بازبینی
    0.06
     πριν
    0.06
     Cru
    0.06
     Camel
    0.06
     ActionBar
    0.06
    omaly
    0.06
    hopefully
    0.06
    TECTED
    0.06
    om
    0.06
    Activations Density 0.030%

    No Known Activations