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. 21813
    Prev
    Next
    INDEX
    Explanations

    structured data snippets

    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
    ayı
    -0.07
     sollte
    -0.07
    .alpha
    -0.07
    female
    -0.07
    Im
    -0.07
     birkaç
    -0.07
    JC
    -0.06
    LEV
    -0.06
     layout
    -0.06
     Im
    -0.06
    POSITIVE LOGITS
    Quaternion
    0.07
    貝
    0.06
    CDF
    0.06
    aily
    0.06
     aqu
    0.06
    ArgumentException
    0.06
    .makedirs
    0.06
     shalt
    0.06
     Instantiate
    0.06
    rw
    0.06
    Activations Density 0.034%

    No Known Activations