© 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. 108984
    Prev
    Next
    INDEX
    Explanations

    erase

    np_max-act · gemini-2.0-flash

    This neuron detects terms that denote removal or wiping out—words like erase, erasing, erased, erases, obliterate, etc.

    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
     платеж
    -0.07
    405
    -0.06
    Alternatively
    -0.06
    12
    -0.06
     renowned
    -0.06
    Christmas
    -0.06
    weekday
    -0.06
     แพ
    -0.06
    amily
    -0.06
     北
    -0.06
    POSITIVE LOGITS
     erase
    0.10
     erosion
    0.09
     erased
    0.08
    ERING
    0.07
    ��
    0.07
    丝
    0.07
    ρωση
    0.07
    LETED
    0.07
     Archive
    0.07
     eradicate
    0.07
    Activations Density 0.006%

    No Known Activations