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. 15-RESID-POST-AA
    6. 120265
    Prev
    Next
    INDEX
    Explanations

    adjusted

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     qué
    -0.06
    ders
    -0.06
     À
    -0.06
     mij
    -0.06
     dzie
    -0.06
     velice
    -0.06
    ครอบ
    -0.06
    TECT
    -0.06
     nIndex
    -0.06
     Dam
    -0.06
    POSITIVE LOGITS
    aviolet
    0.06
     enslaved
    0.06
    rophe
    0.06
     **/↵↵
    0.06
    (nav
    0.06
    止
    0.06
     بود
    0.06
     ET
    0.06
    18
    0.06
    韓
    0.06
    Activations Density 0.000%

    No Known Activations