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. 78698
    Prev
    Next
    INDEX
    Explanations

    search

    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
    reds
    -0.07
     Sud
    -0.06
    eygamber
    -0.06
     })
    ↵
    -0.06
     Peygamber
    -0.06
    thresh
    -0.06
    anol
    -0.06
    yah
    -0.06
    wpdb
    -0.06
    Customer
    -0.06
    POSITIVE LOGITS
     somewhat
    0.07
    Blur
    0.07
    मन
    0.06
    ={[↵
    0.06
     USED
    0.06
     buộc
    0.06
     replaces
    0.06
    	exit
    0.06
    πουλος
    0.06
     behold
    0.06
    Activations Density 0.015%

    No Known Activations