Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 27359
    Prev
    Next
    INDEX
    Explanations

    program

    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
     setuptools
    -0.07
     Polyester
    -0.07
    Tele
    -0.07
    izio
    -0.07
     tritur
    -0.06
     ihnen
    -0.06
     quella
    -0.06
     isolate
    -0.06
    /device
    -0.06
     braking
    -0.06
    POSITIVE LOGITS
     phosphory
    0.07
     Californ
    0.06
     Newsletter
    0.06
    หร
    0.06
     pl
    0.06
     Jeremiah
    0.06
     APIs
    0.06
     ‎
    0.06
    _New
    0.06
    ंघ
    0.06
    Activations Density 0.009%

    No Known Activations