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. 99608
    Prev
    Next
    INDEX
    Explanations

    binding

    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
     tsunami
    -0.07
    ucket
    -0.06
     altern
    -0.06
    Berlin
    -0.06
     frase
    -0.06
     plates
    -0.06
     sections
    -0.06
    α
    -0.06
    MAL
    -0.06
     chees
    -0.06
    POSITIVE LOGITS
    Toast
    0.07
     Embassy
    0.07
     صلى
    0.07
     m�
    0.06
     více
    0.06
    紅
    0.06
     ECS
    0.06
    binding
    0.06
    ıl
    0.06
     ऑ
    0.06
    Activations Density 0.017%

    No Known Activations