Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 110920
    Prev
    Next
    INDEX
    Explanations

    )

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    몬
    -0.07
     infuri
    -0.06
    ่าต
    -0.06
    Model
    -0.06
     spree
    -0.06
     Cork
    -0.06
     emperor
    -0.06
    であ
    -0.06
     Escort
    -0.06
     brigade
    -0.06
    POSITIVE LOGITS
    τι
    0.07
    Failed
    0.07
     political
    0.06
    ющий
    0.06
    adius
    0.06
    acts
    0.06
    기의
    0.06
    _PAGES
    0.06
     είχαν
    0.06
    	ASSERT
    0.06
    Activations Density 0.001%

    No Known Activations