© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89852
    Prev
    Next
    INDEX
    Explanations

    Code and configurations

    np_max-act · gemini-2.0-flash

    This neuron activates on CamelCase identifier tokens (mixed-case names typical of code variables, types, and function 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
    ']:
    -0.07
     Procedures
    -0.07
    <main
    -0.06
    <System
    -0.06
    adioButton
    -0.06
    iforn
    -0.06
    ukes
    -0.06
    refix
    -0.06
    .UserId
    -0.06
    udy
    -0.06
    POSITIVE LOGITS
     aquatic
    0.07
     разм
    0.07
     obrig
    0.07
    oreal
    0.07
     henne
    0.06
    oen
    0.06
     prend
    0.06
    _PAYLOAD
    0.06
     lane
    0.06
    acağı
    0.06
    Activations Density 0.035%

    No Known Activations