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. 110783
    Prev
    Next
    INDEX
    Explanations

    root

    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
     chapters
    -0.06
     účin
    -0.06
     Jiří
    -0.06
     fontStyle
    -0.06
     Grip
    -0.06
    _difference
    -0.06
    _->
    -0.06
    tfoot
    -0.06
    Vin
    -0.06
    λογία
    -0.06
    POSITIVE LOGITS
     struct
    0.07
     prevented
    0.06
     egal
    0.06
     本
    0.06
    instr
    0.06
    签
    0.06
    terrorism
    0.06
    ertificate
    0.06
    ообраз
    0.06
    روه
    0.06
    Activations Density 0.002%

    No Known Activations