© 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. 55547
    Prev
    Next
    INDEX
    Explanations

    employment

    np_max-act · gemini-2.0-flash

    The neuron fires on direct second‐person, positive or encouraging statements (e.g. “you have successfully…,” “invite you,” “opportunity to join you,” etc.).

    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
     Σα
    -0.06
     обязательно
    -0.06
     Shawn
    -0.06
    .Layout
    -0.06
     Helper
    -0.06
     shower
    -0.06
    ,str
    -0.06
     stil
    -0.06
     hitch
    -0.06
     pager
    -0.06
    POSITIVE LOGITS
    _static
    0.07
     сторін
    0.07
     dispon
    0.06
     Equals
    0.06
    itian
    0.06
     connectionString
    0.06
    �습니다
    0.06
    _working
    0.06
     denne
    0.06
    umm
    0.06
    Activations Density 0.167%

    No Known Activations