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. 93593
    Prev
    Next
    INDEX
    Explanations

    ruthless

    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
     blurry
    -0.07
    鲜
    -0.07
    ักงาน
    -0.06
    اطعة
    -0.06
    鮮
    -0.06
     часа
    -0.06
     duygu
    -0.06
     airplane
    -0.06
     Ιω
    -0.06
     headset
    -0.06
    POSITIVE LOGITS
     ruthless
    0.12
     cout
    0.07
     Ruth
    0.07
     Libertarian
    0.07
     enumerate
    0.07
     ruth
    0.06
    itempty
    0.06
    atory
    0.06
    [msg
    0.06
    Sigma
    0.06
    Activations Density 0.007%

    No Known Activations