Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 77760
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ondrous
    -0.07
    '].
    -0.06
     Cup
    -0.06
    ]==
    -0.06
    pack
    -0.06
    ertext
    -0.06
    gl
    -0.06
     "&
    -0.06
     Evil
    -0.06
    -gl
    -0.06
    POSITIVE LOGITS
     FUCK
    0.06
     Nad
    0.06
    ActionBar
    0.06
     ayır
    0.06
     taxpayers
    0.06
    ?)↵
    0.06
     collider
    0.06
     maliyet
    0.06
    apGestureRecognizer
    0.06
    McC
    0.06
    Activations Density 0.015%

    No Known Activations