Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 125412
    Prev
    Next
    INDEX
    Explanations

    own

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “own,” especially in phrases like “create my own ….”

    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
    throw
    -0.06
     nightmare
    -0.06
     shot
    -0.06
     latency
    -0.06
    69
    -0.06
     býval
    -0.06
     FY
    -0.06
     decisions
    -0.06
    partial
    -0.06
    cust
    -0.06
    POSITIVE LOGITS
     나는
    0.07
    ":"'
    0.06
    lightly
    0.06
    \Php
    0.06
     ettik
    0.06
    .readString
    0.06
     đầy
    0.06
    (cps
    0.06
     CHP
    0.06
     (...
    0.06
    Activations Density 0.013%

    No Known Activations