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. 81288
    Prev
    Next
    INDEX
    Explanations

    are

    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
    _pet
    -0.07
    .ide
    -0.06
     Geld
    -0.06
    ullet
    -0.06
    Rev
    -0.06
     WARN
    -0.06
    Facade
    -0.06
    /public
    -0.05
     yarat
    -0.05
     засобів
    -0.05
    POSITIVE LOGITS
     animations
    0.08
    ्ठ
    0.06
     trapped
    0.06
     bitter
    0.06
     libre
    0.06
     wallpapers
    0.06
    Torrent
    0.06
    _an
    0.06
     abrir
    0.06
    dance
    0.06
    Activations Density 0.031%

    No Known Activations