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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 122570
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
     Boss
    -0.07
     parasites
    -0.06
    ..."
    -0.06
     ts
    -0.06
     boss
    -0.06
     Capcom
    -0.06
     GFP
    -0.06
    ่าว
    -0.06
     Luc
    -0.06
    Nic
    -0.06
    POSITIVE LOGITS
    (pattern
    0.06
    ystore
    0.06
     됩니다
    0.06
     或
    0.06
    ierge
    0.06
    -hover
    0.06
    ‌است
    0.06
    .minecraft
    0.06
     мяг
    0.06
    \grid
    0.06
    Activations Density 0.001%

    No Known Activations