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. 19-RESID-POST-AA
    6. 59782
    Prev
    Next
    INDEX
    Explanations

    Element

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ött
    -0.07
    τηγορία
    -0.06
    caler
    -0.06
    .getC
    -0.06
    组
    -0.06
     pprint
    -0.06
     Millet
    -0.06
     ejac
    -0.06
    <Tuple
    -0.06
    preci
    -0.06
    POSITIVE LOGITS
    VISION
    0.07
     element
    0.07
    “One
    0.07
    Dash
    0.07
    Too
    0.07
     Thinking
    0.07
    756
    0.07
     elsewhere
    0.07
     })(
    0.06
    Element
    0.06
    Activations Density 0.014%

    No Known Activations