© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 9032
    Prev
    Next
    INDEX
    Explanations

    Mixed-quality text excerpts

    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
    COUNT
    -0.07
     jsx
    -0.07
    чик
    -0.07
    -material
    -0.07
     فوتبال
    -0.07
     nowrap
    -0.07
    kaz
    -0.06
     tornado
    -0.06
     здат
    -0.06
     Kot
    -0.06
    POSITIVE LOGITS
    SingleNode
    0.07
     Dogs
    0.06
     Chloe
    0.06
    liqu
    0.06
    modifier
    0.06
     stu
    0.06
     Olympus
    0.06
    oste
    0.06
    Alchemy
    0.06
     cải
    0.06
    Activations Density 0.000%

    No Known Activations