© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95492
    Prev
    Next
    INDEX
    Explanations

    notes or disclaimers

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _CT
    -0.07
    Coder
    -0.07
    (scanner
    -0.06
    IVERY
    -0.06
    JKLM
    -0.06
    цип
    -0.06
    criptive
    -0.06
    شار
    -0.06
     TestBed
    -0.06
    ApplicationContext
    -0.06
    POSITIVE LOGITS
    .teacher
    0.07
    )}↵
    0.06
     ^{}
    0.06
     Vimeo
    0.06
     hük
    0.06
     tăng
    0.06
     //!
    0.06
     :=↵
    0.06
     تعریف
    0.06
     الى
    0.06
    Activations Density 0.126%

    No Known Activations