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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 95631
    Prev
    Next
    INDEX
    Explanations

    coding questions

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    币
    -0.06
     مثال
    -0.06
    _tc
    -0.06
    (tb
    -0.06
    ivate
    -0.06
     başına
    -0.06
    adele
    -0.06
    拥有
    -0.06
    \n
    -0.06
     gsi
    -0.06
    POSITIVE LOGITS
     FLASH
    0.07
     Brother
    0.06
    .GET
    0.06
     realities
    0.06
    /download
    0.06
     Kiev
    0.06
     центра
    0.06
     Arrow
    0.06
     analyzes
    0.06
     đốc
    0.06
    Activations Density 0.197%

    No Known Activations