© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 57398
    Prev
    Next
    INDEX
    Explanations

    welcome

    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
     Cz
    -0.07
     /\.(
    -0.07
     Orr
    -0.07
     seventeen
    -0.07
     surpassed
    -0.07
     Dispatcher
    -0.07
    stein
    -0.07
     iterator
    -0.06
     hitting
    -0.06
    ครง
    -0.06
    POSITIVE LOGITS
     welcoming
    0.12
     welcome
    0.11
     Welcome
    0.09
    Welcome
    0.08
     welcomed
    0.08
     Wel
    0.08
    welcome
    0.07
     Welch
    0.07
     Wales
    0.07
    Follow
    0.07
    Activations Density 0.008%

    No Known Activations