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. 11-RESID-POST-AA
    6. 118401
    Prev
    Next
    INDEX
    Explanations

    minerals

    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_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
    "You
    -0.07
     Wang
    -0.07
     Tak
    -0.07
     Bang
    -0.07
     Kamp
    -0.07
    jected
    -0.07
     Attack
    -0.07
     Barton
    -0.07
     Pop
    -0.07
     cot
    -0.07
    POSITIVE LOGITS
     minerals
    0.11
     mineral
    0.09
     Minerals
    0.09
     Mineral
    0.08
    rema
    0.07
    ina
    0.07
     natural
    0.07
     мік
    0.07
     chili
    0.07
     матері
    0.06
    Activations Density 0.003%

    No Known Activations