© 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. 11-RESID-POST-AA
    6. 36704
    Prev
    Next
    INDEX
    Explanations

    explanations and problems

    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
    RAY
    -0.07
    imulation
    -0.07
     this
    -0.07
     national
    -0.07
    �u
    -0.06
    atching
    -0.06
     This
    -0.06
     these
    -0.06
    These
    -0.06
     erupt
    -0.06
    POSITIVE LOGITS
     [↵↵
    0.07
     ukaz
    0.07
    .aspx
    0.06
    τει
    0.06
    のか
    0.06
    ,同时
    0.06
     були
    0.06
    slick
    0.06
       
    0.06
    .project
    0.06
    Activations Density 0.063%

    No Known Activations