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. 54335
    Prev
    Next
    INDEX
    Explanations

    drama

    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
    .TestCheck
    -0.07
     Defaults
    -0.07
    781
    -0.07
    .Nodes
    -0.07
     Orb
    -0.06
     eing
    -0.06
    ussian
    -0.06
     Isle
    -0.06
     goats
    -0.06
    IconModule
    -0.06
    POSITIVE LOGITS
     Dram
    0.11
     dramatic
    0.11
     drama
    0.10
     dramas
    0.09
     Drama
    0.09
     dramatically
    0.09
    ,D
    0.08
     traged
    0.07
     dram
    0.07
    rama
    0.07
    Activations Density 0.009%

    No Known Activations