© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 110237
    Prev
    Next
    INDEX
    Explanations

    Healthy/organic food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beneficial
    -0.07
    操作
    -0.07
     las
    -0.07
    (end
    -0.07
    emiah
    -0.07
     Tue
    -0.07
    cta
    -0.07
     symbolic
    -0.07
     regularly
    -0.06
     TWO
    -0.06
    POSITIVE LOGITS
    ：“
    0.06
    ">';↵
    0.06
    _website
    0.06
    那么
    0.06
     AVCapture
    0.06
     للت
    0.06
     Jonas
    0.06
     борь
    0.06
    สาห
    0.06
    ουλ
    0.05
    Activations Density 0.129%

    No Known Activations