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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 22521
    Prev
    Next
    INDEX
    Explanations

    get

    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
    orld
    -0.07
    mars
    -0.07
    اشة
    -0.07
    (""))↵
    -0.07
     Timestamp
    -0.06
     Salvation
    -0.06
    "}}>↵
    -0.06
     Hakk
    -0.06
    んと
    -0.06
    "}}↵
    -0.06
    POSITIVE LOGITS
     QVector
    0.07
    uuml
    0.07
     meetup
    0.06
     disrupting
    0.06
     Initi
    0.06
    decess
    0.06
     distinctive
    0.06
    護
    0.06
     alter
    0.06
     ug
    0.06
    Activations Density 0.001%

    No Known Activations