Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 110549
    Prev
    Next
    INDEX
    Explanations

    choose your own adventure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icao
    -0.07
     enraged
    -0.07
     Bek
    -0.07
    巴
    -0.06
     enth
    -0.06
    bh
    -0.06
     defect
    -0.06
     landmark
    -0.06
     wal
    -0.06
    installed
    -0.06
    POSITIVE LOGITS
     kell
    0.07
    aliz
    0.06
    ],&
    0.06
    (dm
    0.06
    .Fail
    0.06
     Voy
    0.06
    텔
    0.06
     civ
    0.06
    .Logger
    0.06
    ]/
    0.06
    Activations Density 0.016%

    No Known Activations