© 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. 90665
    Prev
    Next
    INDEX
    Explanations

    sports, teams, and players

    np_max-act · gemini-2.0-flash

    The neuron detects references to someone’s past roles or former affiliations (e.g., tokens like “former”).

    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
     Girls
    -0.08
     bubbles
    -0.06
    perf
    -0.06
     staining
    -0.06
     кост
    -0.06
     expertise
    -0.06
    ,exports
    -0.06
    rogen
    -0.06
     scrolls
    -0.06
    animated
    -0.06
    POSITIVE LOGITS
     、
    0.06
     době
    0.06
     Něm
    0.06
     světa
    0.06
    _CYCLE
    0.06
    .ModelAdmin
    0.06
     اتاق
    0.06
    .Word
    0.06
    (il
    0.06
     уст
    0.06
    Activations Density 0.067%

    No Known Activations