© 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
    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. 12637
    Prev
    Next
    INDEX
    Explanations

    supervisors or managers

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of management‐level job titles—especially the word “manager” (and its close variants) in position 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
    About
    -0.06
    sorry
    -0.06
     belong
    -0.06
    modation
    -0.06
    -design
    -0.06
    teg
    -0.06
    177
    -0.06
    _net
    -0.06
     png
    -0.06
     Surgical
    -0.06
    POSITIVE LOGITS
    İ
    0.07
    -mf
    0.07
    .xrLabel
    0.06
    -single
    0.06
    PTS
    0.06
     میل
    0.06
     jedním
    0.06
     economical
    0.06
    NavItem
    0.06
    lain
    0.06
    Activations Density 0.035%

    No Known Activations