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. 21439
    Prev
    Next
    INDEX
    Explanations

    Bills and billing

    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
    において
    -0.07
    terminal
    -0.07
    iscopal
    -0.06
     rab
    -0.06
     Trung
    -0.06
    mailer
    -0.06
    Mad
    -0.06
     coordination
    -0.06
    ót
    -0.06
    apot
    -0.06
    POSITIVE LOGITS
     onboard
    0.06
    ynthesis
    0.06
     فو
    0.06
     Artifact
    0.06
    eth
    0.06
    иж
    0.06
    (os
    0.06
    -app
    0.06
     Barcode
    0.06
     Dispose
    0.06
    Activations Density 0.005%

    No Known Activations