© 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. 37999
    Prev
    Next
    INDEX
    Explanations

    deposition

    np_max-act · gemini-2.0-flash

    the word “deposition” (and its plural “depositions”) in legal documents.

    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
    朋友
    -0.07
     lg
    -0.06
    Thumbnail
    -0.06
    ชาย
    -0.06
    Elite
    -0.06
     Wild
    -0.06
     alarms
    -0.06
    ")}↵
    -0.06
    стр
    -0.06
    ynchronization
    -0.06
    POSITIVE LOGITS
    (SQLException
    0.08
     konci
    0.07
     châu
    0.06
     conson
    0.06
    월까지
    0.06
    Much
    0.06
    lası
    0.06
    _normalized
    0.06
     Latter
    0.06
     stepping
    0.06
    Activations Density 0.001%

    No Known Activations