© 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. 13368
    Prev
    Next
    INDEX
    Explanations

    college

    np_max-act · gemini-2.0-flash

    The neuron fires on references to college and its financing (tuition, costs, grants, scholarships, enrollment statistics, 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
     scient
    -0.07
    -handler
    -0.07
    Number
    -0.06
    sections
    -0.06
     HEIGHT
    -0.06
    -am
    -0.06
    -shop
    -0.06
    ‘
    -0.06
     حتی
    -0.06
    360
    -0.06
    POSITIVE LOGITS
     OWNER
    0.06
    uids
    0.06
     outer
    0.06
     Hodg
    0.06
     jew
    0.06
     ea
    0.06
    赏
    0.06
     setTime
    0.06
    劃
    0.06
     melanch
    0.06
    Activations Density 0.013%

    No Known Activations