© 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. 6575
    Prev
    Next
    INDEX
    Explanations

    hot

    np_max-act · gemini-2.0-flash

    The neuron fires on descriptive adjectives—especially compound or suffixed adjectives like “bottomless,” “level-headed,” or “hot-headed.”

    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
    عف
    -0.08
     Nights
    -0.07
    욱
    -0.07
    ssc
    -0.07
    컵
    -0.07
     VIII
    -0.07
     हव
    -0.06
    sku
    -0.06
     Launcher
    -0.06
    ạch
    -0.06
    POSITIVE LOGITS
     contrib
    0.07
     arreglo
    0.07
     alumnos
    0.06
     LOOP
    0.06
     pepp
    0.06
     misog
    0.06
     dot
    0.06
     hombres
    0.06
    討
    0.06
     quần
    0.06
    Activations Density 0.178%

    No Known Activations