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. 123593
    Prev
    Next
    INDEX
    Explanations

    books

    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
     Apr
    -0.07
    Authenticated
    -0.06
     рублей
    -0.06
     招
    -0.06
    出去
    -0.06
     withRouter
    -0.06
    .choice
    -0.06
    ~-
    -0.06
    누
    -0.06
    .Setter
    -0.06
    POSITIVE LOGITS
     aroma
    0.06
     Manit
    0.06
    	View
    0.06
     davranış
    0.06
    대학교
    0.06
    unal
    0.06
    桂
    0.05
    �은
    0.05
    rage
    0.05
    conduct
    0.05
    Activations Density 0.006%

    No Known Activations