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. 21299
    Prev
    Next
    INDEX
    Explanations

    run

    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
    ANEL
    -0.07
    .getLeft
    -0.06
     srpna
    -0.06
    .absolute
    -0.06
    Timeout
    -0.06
     hầu
    -0.06
    Jac
    -0.06
    іш
    -0.06
    anno
    -0.06
     OPTIONAL
    -0.06
    POSITIVE LOGITS
     React
    0.07
    َو
    0.07
     gerçekleştir
    0.07
     Next
    0.07
     GO
    0.07
    .character
    0.07
    olve
    0.06
     Suite
    0.06
    uestion
    0.06
     attributes
    0.06
    Activations Density 0.010%

    No Known Activations