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. 21766
    Prev
    Next
    INDEX
    Explanations

    depending

    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
    画
    -0.06
     پیام
    -0.06
    очных
    -0.06
     egregious
    -0.06
     Gap
    -0.06
    рех
    -0.06
    >m
    -0.06
    MAP
    -0.06
     scoring
    -0.05
    .Interop
    -0.05
    POSITIVE LOGITS
    (names
    0.07
    (ac
    0.07
    (DIS
    0.07
    chang
    0.06
    ปก
    0.06
     FIELD
    0.06
    .loc
    0.06
     unsustainable
    0.06
    <l
    0.06
     kappa
    0.06
    Activations Density 0.017%

    No Known Activations