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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 123177
    Prev
    Next
    INDEX
    Explanations

    designate

    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
     Kol
    -0.07
     άν
    -0.07
     nấu
    -0.07
    192
    -0.07
     Jahre
    -0.06
    “So
    -0.06
     nikdo
    -0.06
     stumbled
    -0.06
     ol
    -0.06
    [url
    -0.06
    POSITIVE LOGITS
     designated
    0.11
     designation
    0.09
     designate
    0.09
     Cunningham
    0.08
    dělení
    0.07
    ATING
    0.07
     욕
    0.07
    ¤
    0.07
     номер
    0.07
    dess
    0.07
    Activations Density 0.006%

    No Known Activations