© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 66621
    Prev
    Next
    INDEX
    Explanations

    strategic routes and access points

    np_max-act · gemini-2.0-flash

    references to military operations and strategic locations during wartime.

    oai_token-act-pair · gpt-4o-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
    Incoming
    -0.07
    bove
    -0.07
    Mob
    -0.06
    Monitor
    -0.06
     Shows
    -0.06
     Mod
    -0.06
     Champion
    -0.06
     معت
    -0.06
     Suppliers
    -0.06
     BÖL
    -0.06
    POSITIVE LOGITS
     지금
    0.07
    碎
    0.07
     healthy
    0.07
     groupBox
    0.07
    -hidden
    0.06
    ร
    0.06
     toJson
    0.06
     cosmos
    0.06
     hely
    0.06
    ابة
    0.06
    Activations Density 0.020%

    No Known Activations