© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 92410
    Prev
    Next
    INDEX
    Explanations

    also

    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
     chromium
    -0.07
     Extract
    -0.06
     scanner
    -0.06
    __["
    -0.06
     Covers
    -0.06
     gratitude
    -0.06
     }};↵
    -0.06
     Draft
    -0.06
    Transfer
    -0.06
     Fourth
    -0.06
    POSITIVE LOGITS
     SMALL
    0.07
    σμο
    0.07
    sku
    0.06
     Chúa
    0.06
    /off
    0.06
    ワイト
    0.06
    /save
    0.06
    lbl
    0.06
    -da
    0.06
    ỉ
    0.06
    Activations Density 0.001%

    No Known Activations