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

    Neuronpedia

    Jacobian LensNEW
    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. 56823
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the chemical abbreviation “PGE 2” (prostaglandin E2) or its component tokens (“E” followed by “2”).

    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
    ediği
    -0.07
    axies
    -0.07
    όν
    -0.06
    森
    -0.06
    ِن
    -0.06
     mm
    -0.06
    われる
    -0.06
    escription
    -0.06
    Opts
    -0.06
     prevail
    -0.06
    POSITIVE LOGITS
     پرداز
    0.06
    �
    0.06
    _delta
    0.06
    Ό
    0.06
     nuanced
    0.06
     doubles
    0.06
     external
    0.06
    'à
    0.06
     crafting
    0.06
     vị
    0.06
    Activations Density 0.003%

    No Known Activations