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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 86103
    Prev
    Next
    INDEX
    Explanations

    United

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting occurrences of “United States.”

    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
    Marca
    -0.07
    494
    -0.07
    ap
    -0.07
    帕
    -0.07
     barn
    -0.07
     Crop
    -0.07
    m
    -0.07
    34
    -0.07
     Mak
    -0.07
     crap
    -0.07
    POSITIVE LOGITS
     United
    0.14
    United
    0.08
    联合
    0.08
     Viet
    0.08
     userModel
    0.07
    ulses
    0.07
     послед
    0.07
    IRST
    0.07
    /socket
    0.07
    UInt
    0.07
    Activations Density 0.024%

    No Known Activations