© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 93414
    Prev
    Next
    INDEX
    Explanations

    27

    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
    γραφή
    -0.07
     reward
    -0.06
    -ajax
    -0.06
    HttpResponse
    -0.06
    orders
    -0.06
    -memory
    -0.06
    Product
    -0.06
     lakes
    -0.06
     allies
    -0.06
    ome
    -0.06
    POSITIVE LOGITS
    78
    0.08
     эффектив
    0.07
    chrono
    0.07
     PIXEL
    0.07
    πτυ
    0.07
    858
    0.07
    457
    0.06
    28
    0.06
     scrutin
    0.06
    !'
    0.06
    Activations Density 0.001%

    No Known Activations