Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84620
    Prev
    Next
    INDEX
    Explanations

    case

    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
    ](
    -0.07
     nov
    -0.07
    =is
    -0.06
     modifiers
    -0.06
     juices
    -0.06
    shows
    -0.06
     FIRE
    -0.06
    ITION
    -0.06
     tiles
    -0.05
    ATOR
    -0.05
    POSITIVE LOGITS
     đội
    0.08
     bq
    0.07
     berg
    0.07
     dpi
    0.06
    fal
    0.06
     defaultCenter
    0.06
     graphene
    0.06
     jedem
    0.06
     你
    0.06
    .assertIs
    0.06
    Activations Density 0.002%

    No Known Activations