Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 123470
    Prev
    Next
    INDEX
    Explanations

    Myths, speech, and business

    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
    een
    -0.06
     служби
    -0.06
    озем
    -0.06
    BindView
    -0.06
    nod
    -0.06
     geçen
    -0.06
    كون
    -0.06
     имеет
    -0.06
    战斗
    -0.06
     Beirut
    -0.06
    POSITIVE LOGITS
     نخ
    0.07
    ).^
    0.07
    TCP
    0.07
     Telephone
    0.07
     clarification
    0.07
    gar
    0.06
     radar
    0.06
     xmax
    0.06
     vector
    0.06
    FH
    0.06
    Activations Density 0.002%

    No Known Activations