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. 78686
    Prev
    Next
    INDEX
    Explanations

    bullet points, lists

    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
    NG
    -0.06
    Redux
    -0.06
    -unused
    -0.06
     Wisdom
    -0.06
    (pts
    -0.06
    ALL
    -0.06
    ASF
    -0.06
    actory
    -0.06
    -setting
    -0.06
     integer
    -0.06
    POSITIVE LOGITS
     jur
    0.07
    coli
    0.06
     küt
    0.06
    .tasks
    0.06
     straně
    0.06
     민
    0.06
     Zuk
    0.06
    شنامه
    0.06
     jj
    0.06
     matrimon
    0.06
    Activations Density 0.097%

    No Known Activations