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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 99743
    Prev
    Next
    INDEX
    Explanations

    canvas

    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
    'We
    -0.07
     То
    -0.07
     fragmented
    -0.07
     hardly
    -0.07
     Virus
    -0.06
    _timeline
    -0.06
    ople
    -0.06
    political
    -0.06
     Roo
    -0.06
    ouston
    -0.06
    POSITIVE LOGITS
     концеп
    0.07
    ️
    0.07
     nostalgia
    0.06
    Щ
    0.06
    quia
    0.06
     athletics
    0.06
    éf
    0.06
     ®
    0.06
    岸
    0.06
     потол
    0.06
    Activations Density 0.004%

    No Known Activations