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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 122376
    Prev
    Next
    INDEX
    Explanations

    the

    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
     DOES
    -0.06
     bil
    -0.06
     railways
    -0.06
     STA
    -0.06
     Expl
    -0.06
     trovare
    -0.06
     Bil
    -0.06
    对
    -0.06
     ad
    -0.06
     가까
    -0.06
    POSITIVE LOGITS
    .nil
    0.07
     },{↵
    0.07
    ="↵
    0.06
     assum
    0.06
    .select
    0.06
     использовани
    0.06
    odont
    0.06
    -piece
    0.06
     @@↵
    0.06
    ``↵
    0.06
    Activations Density 0.121%

    No Known Activations