© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95437
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and initialisms

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     booster
    -0.06
    очь
    -0.06
    .plugin
    -0.06
    .marker
    -0.06
    	thread
    -0.06
     finder
    -0.06
    -bearing
    -0.06
    -facing
    -0.06
     archivo
    -0.06
    .addListener
    -0.06
    POSITIVE LOGITS
    ently
    0.08
     Comments
    0.07
     thì
    0.06
    805
    0.06
     uden
    0.06
     vamp
    0.06
     YE
    0.06
    Require
    0.06
    .Exit
    0.06
    Bear
    0.06
    Activations Density 0.454%

    No Known Activations