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. 80613
    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
    _ann
    -0.07
    urface
    -0.07
     Crossing
    -0.07
    лемент
    -0.06
    letal
    -0.06
    .Named
    -0.06
     Ra
    -0.06
    .fm
    -0.06
    blink
    -0.06
    orph
    -0.06
    POSITIVE LOGITS
    =<?=
    0.08
    pedo
    0.06
     baise
    0.06
    СО
    0.06
    {{--
    0.06
               
    0.06
    (dc
    0.06
     Shortcut
    0.06
     Propel
    0.06
    CSS
    0.06
    Activations Density 0.001%

    No Known Activations