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. 81300
    Prev
    Next
    INDEX
    Explanations

    Medical figure descriptions

    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
     scour
    -0.07
     Fiona
    -0.06
    -width
    -0.06
     ser
    -0.06
     publications
    -0.06
     루
    -0.06
    」
    -0.06
     Kara
    -0.06
     Car
    -0.06
    tees
    -0.06
    POSITIVE LOGITS
    _ELEMENTS
    0.07
    $status
    0.07
     $\
    0.07
    .DateField
    0.07
    865
    0.06
     Vendor
    0.06
    .rand
    0.06
    weakSelf
    0.06
    eg
    0.06
     prostředí
    0.06
    Activations Density 0.004%

    No Known Activations