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. 104284
    Prev
    Next
    INDEX
    Explanations

    Events and shows

    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
     list
    -0.07
    ована
    -0.07
    List
    -0.07
     kernel
    -0.06
     stocks
    -0.06
     userList
    -0.06
    LastError
    -0.06
     Amazon
    -0.06
     antibiotics
    -0.06
    ल
    -0.06
    POSITIVE LOGITS
     sher
    0.07
     rely
    0.07
    paginator
    0.06
    -important
    0.06
    azes
    0.06
    ermo
    0.06
    .DisplayName
    0.06
     üzerinden
    0.06
     ‐
    0.06
    革
    0.06
    Activations Density 0.087%

    No Known Activations