© 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. 11-RESID-POST-AA
    11. 34152
    Prev
    Next
    INDEX
    Explanations

    response

    np_max-act · gemini-2.0-flash

    references to specific AI models and their functionalities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     servants
    -0.07
    เสน
    -0.06
    .atom
    -0.06
     mol
    -0.06
     downtown
    -0.06
    [cnt
    -0.06
     Appeals
    -0.06
    ainless
    -0.06
    خی
    -0.06
    37
    -0.06
    POSITIVE LOGITS
     resizing
    0.07
    .Speed
    0.07
    ague
    0.06
     hareket
    0.06
     deep
    0.06
    tls
    0.06
    gerald
    0.06
     flashed
    0.06
    missing
    0.06
     handles
    0.06
    Activations Density 0.023%

    No Known Activations