© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 27080
    Prev
    Next
    INDEX
    Explanations

    code

    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
     kiến
    -0.08
    into
    -0.07
     um
    -0.07
    around
    -0.07
    нила
    -0.06
     whereabouts
    -0.06
     spun
    -0.06
     wordt
    -0.06
     분
    -0.06
     Term
    -0.06
    POSITIVE LOGITS
    ediator
    0.07
    ング
    0.07
    _nama
    0.06
    <Entry
    0.06
         ↵↵
    0.06
    ้ม
    0.06
    .DOM
    0.06
     fighter
    0.06
     capit
    0.06
    .Look
    0.06
    Activations Density 0.019%

    No Known Activations