© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 9234
    Prev
    Next
    INDEX
    Explanations

    hole

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “hole” (and its close variants) in the text.

    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
    atten
    -0.08
     Scripture
    -0.07
    Rad
    -0.06
    umericUpDown
    -0.06
     Crawford
    -0.06
    COMM
    -0.06
     pastors
    -0.06
     kvinna
    -0.06
    �
    -0.06
     Entertainment
    -0.06
    POSITIVE LOGITS
     Hole
    0.16
     hole
    0.15
     holes
    0.12
    holes
    0.12
    hole
    0.11
    -hole
    0.10
    洞
    0.09
    ole
    0.08
    戸
    0.08
     Holt
    0.08
    Activations Density 0.008%

    No Known Activations