© 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. 7-RESID-POST-AA
    6. 61159
    Prev
    Next
    INDEX
    Explanations

    #include

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tháng
    -0.07
     yaw
    -0.06
    =c
    -0.06
     yok
    -0.06
    =[
    -0.06
    ohen
    -0.06
    dong
    -0.06
     знать
    -0.06
    overall
    -0.06
     `.
    -0.06
    POSITIVE LOGITS
    recur
    0.08
    ункт
    0.07
     καλύ
    0.06
     выраж
    0.06
     lw
    0.06
    "url
    0.06
     PMID
    0.06
    (sizeof
    0.06
    sum
    0.06
     ),
    ↵
    0.06
    Activations Density 0.006%

    No Known Activations