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. 125848
    Prev
    Next
    INDEX
    Explanations

    Prompts

    np_max-act · gemini-2.0-flash

    This neuron detects when the prompt assigns or restates the assistant’s role or profession (e.g., “You are a travel agent,” “You are a meteorologist”).

    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
     Claw
    -0.07
     adolescence
    -0.07
     compound
    -0.07
     FAQ
    -0.06
     AuthenticationService
    -0.06
     parsley
    -0.06
    adastrar
    -0.06
    ahaha
    -0.06
     hypertension
    -0.06
    ousedown
    -0.06
    POSITIVE LOGITS
     vig
    0.07
    _GREEN
    0.07
     lòng
    0.07
     gir
    0.06
     sustain
    0.06
     Career
    0.06
     neglect
    0.06
     manic
    0.06
     đa
    0.06
    _publisher
    0.06
    Activations Density 0.033%

    No Known Activations