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. 104252
    Prev
    Next
    INDEX
    Explanations

    <

    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
    reste
    -0.07
     rented
    -0.07
    рова
    -0.07
     /^\
    -0.06
     Mario
    -0.06
    MAR
    -0.06
     yoga
    -0.06
    Span
    -0.06
    propri
    -0.06
     med
    -0.06
    POSITIVE LOGITS
     기준
    0.06
    �
    0.06
     Auburn
    0.06
     PSI
    0.06
    _BAND
    0.06
    ripsi
    0.06
     Percent
    0.06
    。此
    0.06
     delivering
    0.06
    .“
    0.05
    Activations Density 0.011%

    No Known Activations