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. 54320
    Prev
    Next
    INDEX
    Explanations

    object properties and functions

    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
    jay
    -0.07
    ,__
    -0.06
    َب
    -0.06
     �
    -0.06
    '](
    -0.06
    BUILD
    -0.06
    Latch
    -0.06
    ][
    -0.06
    (new
    -0.06
    )?$
    -0.06
    POSITIVE LOGITS
     《
    0.08
     пут
    0.07
     #-}↵↵
    0.07
    iseconds
    0.06
    특별시
    0.06
    _ios
    0.06
     ='
    0.06
    Những
    0.06
    《
    0.06
     Uncomment
    0.06
    Activations Density 0.047%

    No Known Activations