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. 104218
    Prev
    Next
    INDEX
    Explanations

    -Encoding

    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
    client
    -0.06
     чого
    -0.06
     mnist
    -0.06
     comparator
    -0.06
    ávací
    -0.06
    (master
    -0.06
    ологія
    -0.06
     pä
    -0.06
     tit
    -0.06
     ConnectionState
    -0.06
    POSITIVE LOGITS
    -Encoding
    0.08
    "]){↵
    0.08
    FW
    0.07
    prising
    0.07
     }));↵↵
    0.07
    GAN
    0.06
    /crypto
    0.06
     Rewards
    0.06
    .Quit
    0.06
    rons
    0.06
    Activations Density 0.000%

    No Known Activations