© 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. 73600
    Prev
    Next
    INDEX
    Explanations

    Penn State

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of specific proper names—especially “Penn State” and key figures in the Sandusky scandal (e.g. Sandusky, Paterno, Spanier).

    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
    icular
    -0.07
    Hip
    -0.06
     kimse
    -0.06
     일부
    -0.06
     Canary
    -0.06
    обы
    -0.06
    िब
    -0.06
    unca
    -0.06
     أنه
    -0.06
    润
    -0.06
    POSITIVE LOGITS
     ################
    0.07
     verify
    0.07
     abundant
    0.06
    _len
    0.06
     abandoned
    0.06
     rewritten
    0.06
     bát
    0.06
    (parameters
    0.06
    hasClass
    0.06
     diret
    0.06
    Activations Density 0.001%

    No Known Activations