© 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. 44553
    Prev
    Next
    INDEX
    Explanations

    Positive sentiment

    np_max-act · gemini-2.0-flash

    The neuron activates on positive, supportive language—phrases about being kind or supportive to others (e.g. “being kind to others,” “supporting your friends”).

    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
     purification
    -0.08
     Kardashian
    -0.07
     pharmacy
    -0.06
     hips
    -0.06
     سام
    -0.06
    ную
    -0.06
     benchmarks
    -0.06
     stall
    -0.06
    )**
    -0.06
     theology
    -0.06
    POSITIVE LOGITS
     NYT
    0.07
    ScrollBar
    0.07
    择
    0.07
    .Alpha
    0.07
    _subnet
    0.07
    ProductName
    0.06
     Barcelona
    0.06
    ocurrency
    0.06
    iyor
    0.06
    เขา
    0.06
    Activations Density 0.014%

    No Known Activations