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. 128931
    Prev
    Next
    INDEX
    Explanations

    with

    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
    254
    -0.07
    :href
    -0.07
    Ka
    -0.07
    /play
    -0.06
    에는
    -0.06
    ,也
    -0.06
     حکومت
    -0.06
     başladı
    -0.06
    롭
    -0.06
    ласти
    -0.06
    POSITIVE LOGITS
     converting
    0.07
     convert
    0.07
     Facing
    0.06
    ctor
    0.06
    apters
    0.06
     Cottage
    0.06
     filtered
    0.06
    规范
    0.06
     forward
    0.06
     крит
    0.06
    Activations Density 0.008%

    No Known Activations