© 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. 91631
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron identifies Wikipedia category labels that denote an athlete’s medal achievements (e.g. “Olympic silver medalists for X”).

    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
    igne
    -0.07
    чим
    -0.06
    专业
    -0.06
    .serial
    -0.06
    itol
    -0.06
    φό
    -0.06
    ськими
    -0.06
    cano
    -0.06
    Mary
    -0.06
     Ronald
    -0.06
    POSITIVE LOGITS
     avere
    0.07
     delete
    0.06
     envis
    0.06
    ORIZATION
    0.06
    	for
    0.06
     Sugar
    0.06
     MOTOR
    0.06
     AREA
    0.06
     apply
    0.06
     hỗ
    0.06
    Activations Density 0.001%

    No Known Activations