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

    Neuronpedia

    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. 40830
    Prev
    Next
    INDEX
    Explanations

    in

    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
    �
    -0.06
    ブロ
    -0.06
     libre
    -0.06
     SORT
    -0.06
    Você
    -0.06
    tep
    -0.06
    �
    -0.06
    Ě
    -0.06
    еля
    -0.06
    煙
    -0.06
    POSITIVE LOGITS
     AIM
    0.07
     ignored
    0.07
     psychic
    0.07
     din
    0.07
     {};
    0.07
     [];
    0.07
    _PERCENT
    0.07
    outcome
    0.07
    оти
    0.06
     alıyor
    0.06
    Activations Density 0.003%

    No Known Activations