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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 80570
    Prev
    Next
    INDEX
    Explanations

    .NET

    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
     Everest
    -0.07
    Couldn
    -0.07
    getConnection
    -0.06
     się
    -0.06
    conc
    -0.06
     senators
    -0.06
    	graph
    -0.06
     öğret
    -0.06
    talk
    -0.06
     laughing
    -0.06
    POSITIVE LOGITS
     náměstí
    0.07
     neurological
    0.07
    服务器
    0.07
     rectangular
    0.06
     unlink
    0.06
     cuanto
    0.06
    iated
    0.06
     ontvangst
    0.06
    setQuery
    0.06
     affection
    0.06
    Activations Density 0.000%

    No Known Activations