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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 30312
    Prev
    Next
    INDEX
    Explanations

    Miller

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on mentions of musical ensembles and their leaders (band/orchestra names and bandleader names).

    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
    蜘蛛
    -0.06
    ▏▏
    -0.06
    pcl
    -0.06
    ôte
    -0.06
    ंव
    -0.06
    ЙЙ
    -0.06
    .EVT
    -0.06
     vile
    -0.06
    jišť
    -0.06
    ncia
    -0.06
    POSITIVE LOGITS
    ……………………
    0.07
     exports
    0.06
     چین
    0.06
    -object
    0.06
     toddlers
    0.06
     global
    0.06
     пос
    0.06
    Environmental
    0.06
    =[
    0.06
     exported
    0.06
    Activations Density 0.005%

    No Known Activations