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. 111298
    Prev
    Next
    INDEX
    Explanations

    connecting words in lists

    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
    logan
    -0.06
     Clim
    -0.06
     pointless
    -0.06
    พวกเข
    -0.06
     coff
    -0.06
    listen
    -0.06
    _vector
    -0.06
     động
    -0.06
    indexPath
    -0.06
    STIT
    -0.06
    POSITIVE LOGITS
    .surname
    0.07
     freedom
    0.06
    (fig
    0.06
    strain
    0.06
    _overflow
    0.06
    {i
    0.06
    ائی
    0.06
     oi
    0.06
    _SUR
    0.06
    γωγή
    0.06
    Activations Density 0.186%

    No Known Activations