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. 113157
    Prev
    Next
    INDEX
    Explanations

    methods and tools

    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
     piles
    -0.07
     sturdy
    -0.07
    roller
    -0.07
     similarly
    -0.07
     Fitz
    -0.07
     roughly
    -0.07
    (top
    -0.07
    か
    -0.06
    _RE
    -0.06
    .ot
    -0.06
    POSITIVE LOGITS
    Ω
    0.06
    odafone
    0.06
    acted
    0.06
     سع
    0.06
    出版社
    0.05
     rencontrer
    0.05
    OrElse
    0.05
    uez
    0.05
    -xl
    0.05
    .Getenv
    0.05
    Activations Density 0.077%

    No Known Activations