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. 11-RESID-POST-AA
    6. 80745
    Prev
    Next
    INDEX
    Explanations

    Null/false assertions

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antu
    -0.07
    Widget
    -0.07
     linking
    -0.06
    .trigger
    -0.06
    _DS
    -0.06
     tide
    -0.06
    ós
    -0.06
    endcode
    -0.06
     @
    -0.06
    ibox
    -0.06
    POSITIVE LOGITS
     Teknik
    0.07
    ToLeft
    0.07
     Ritch
    0.06
     الب
    0.06
     payout
    0.06
     CSR
    0.06
    gfx
    0.06
     XR
    0.06
     wealthiest
    0.06
     crem
    0.06
    Activations Density 0.008%

    No Known Activations