© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 93651
    Prev
    Next
    INDEX
    Explanations

    benefits

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Collapse
    -0.07
    щини
    -0.07
    어
    -0.07
    قرار
    -0.07
     Manson
    -0.07
    ouncing
    -0.07
     sentenced
    -0.07
    ⠀⠀
    -0.06
     concatenate
    -0.06
    獨
    -0.06
    POSITIVE LOGITS
     benefits
    0.17
     Benefits
    0.13
     benefit
    0.11
     Benefit
    0.09
    Benefits
    0.09
     Beyond
    0.07
     Benef
    0.06
    bf
    0.06
     Sponsored
    0.06
    	lib
    0.06
    Activations Density 0.008%

    No Known Activations