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. 88381
    Prev
    Next
    INDEX
    Explanations

    border

    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
     beside
    -0.08
    [path
    -0.07
    Beyond
    -0.06
    [table
    -0.06
    -cross
    -0.06
     Currently
    -0.06
    Cold
    -0.06
    Entering
    -0.06
     startling
    -0.06
     primo
    -0.06
    POSITIVE LOGITS
    SEE
    0.06
     parentheses
    0.06
    音楽
    0.06
    -posts
    0.06
    ička
    0.06
     Mum
    0.06
     produits
    0.06
     Mour
    0.06
     -------↵
    0.06
     intermediate
    0.06
    Activations Density 0.006%

    No Known Activations