© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89679
    Prev
    Next
    INDEX
    Explanations

    construction of structures

    np_max-act · gemini-2.0-flash

    This neuron selectively fires on occurrences of the Portuguese word “pirâmides” (and its sub-token parts).

    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
    drawable
    -0.06
     battery
    -0.06
     wolf
    -0.06
    IMATION
    -0.06
    EC
    -0.06
    ategorias
    -0.06
     purely
    -0.06
    ÅŸ
    -0.06
    :num
    -0.06
    _HORIZONTAL
    -0.06
    POSITIVE LOGITS
     Lucifer
    0.07
    chandle
    0.07
    edx
    0.07
    xBB
    0.06
     下载
    0.06
     pcl
    0.06
     stool
    0.06
    Если
    0.06
     cara
    0.06
    성이
    0.06
    Activations Density 0.021%

    No Known Activations