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. 21857
    Prev
    Next
    INDEX
    Explanations

    facto

    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
     Kraft
    -0.06
    práv
    -0.06
    اسب
    -0.06
     پیام
    -0.06
     Execute
    -0.06
     احمد
    -0.06
     rằng
    -0.06
     sediment
    -0.06
     Shows
    -0.06
     Apollo
    -0.06
    POSITIVE LOGITS
     clinically
    0.07
    к
    0.07
    Offset
    0.07
     popularity
    0.07
     Ball
    0.07
    oulder
    0.07
    -dr
    0.07
    #undef
    0.07
     INSTANCE
    0.06
    */,
    0.06
    Activations Density 0.006%

    No Known Activations