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. 80791
    Prev
    Next
    INDEX
    Explanations

    Code with numbered parameters

    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
    Mad
    -0.07
    match
    -0.07
    magnitude
    -0.06
     referring
    -0.06
    stdlib
    -0.06
     Quest
    -0.06
     Ottoman
    -0.06
    ออกแบบ
    -0.06
     consent
    -0.06
     legends
    -0.06
    POSITIVE LOGITS
    лючается
    0.07
    /actions
    0.07
    oure
    0.07
    运行
    0.06
     système
    0.06
     serge
    0.06
     ValidationResult
    0.06
    (state
    0.06
    xce
    0.06
     Scarlett
    0.06
    Activations Density 0.007%

    No Known Activations