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. 53859
    Prev
    Next
    INDEX
    Explanations

    there

    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
    creates
    -0.07
     Spor
    -0.06
    Oct
    -0.06
    óng
    -0.06
    Nov
    -0.06
    !!}↵
    -0.06
     Tage
    -0.06
    .BLUE
    -0.06
    .UP
    -0.06
     lehet
    -0.06
    POSITIVE LOGITS
     sử
    0.07
     diferentes
    0.06
    (target
    0.06
    sss
    0.06
    _initializer
    0.06
     troub
    0.06
     dames
    0.06
    닝
    0.06
     timetable
    0.06
    _language
    0.06
    Activations Density 0.006%

    No Known Activations