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. 99531
    Prev
    Next
    INDEX
    Explanations

    which

    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
     REQUIRE
    -0.07
    (header
    -0.07
     START
    -0.06
     сад
    -0.06
     USAGE
    -0.06
    pictures
    -0.06
     �
    -0.06
    _EVAL
    -0.06
     tel
    -0.06
     vive
    -0.05
    POSITIVE LOGITS
     which
    0.08
    اته
    0.07
    which
    0.07
    šit
    0.07
    .InnerText
    0.07
    ومی
    0.07
     Chili
    0.07
    (ent
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    cbc
    0.06
    Activations Density 0.062%

    No Known Activations