© 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. 12082
    Prev
    Next
    INDEX
    Explanations

    agile

    np_max-act · gemini-2.0-flash

    This neuron specifically detects the token “ile,” as it appears in “Agile,” effectively marking occurrences of the word Agile.

    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
     말했다
    -0.07
    .hot
    -0.07
    PosY
    -0.07
     zákaz
    -0.06
     bombed
    -0.06
    eum
    -0.06
     koruy
    -0.06
    (para
    -0.06
    상
    -0.06
    instanc
    -0.06
    POSITIVE LOGITS
     agile
    0.10
     agility
    0.08
    ity
    0.07
     Agile
    0.07
    Git
    0.07
     Gamb
    0.07
     애
    0.07
    IFORM
    0.07
     aws
    0.07
     Agility
    0.07
    Activations Density 0.002%

    No Known Activations