© 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
    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. 25906
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    code documentation and metadata related to software licensing and API structure.

    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
    ACH
    -0.07
    显
    -0.07
    是我
    -0.06
    ach
    -0.06
     Mara
    -0.06
     Hammer
    -0.06
    lech
    -0.06
     Acres
    -0.06
    owers
    -0.06
    	Camera
    -0.06
    POSITIVE LOGITS
    บาท
    0.08
     booklet
    0.07
    -meta
    0.07
     presenting
    0.06
     ho
    0.06
    ليم
    0.06
    ilendir
    0.06
     gboolean
    0.06
     قدر
    0.06
     quảng
    0.06
    Activations Density 0.002%

    No Known Activations