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. 19-RESID-POST-AA
    6. 9878
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quarry
    -0.07
     Ти
    -0.06
    modify
    -0.06
     IconData
    -0.06
     Stacy
    -0.06
    ra
    -0.06
     roar
    -0.06
     Mapper
    -0.06
     Him
    -0.06
     setC
    -0.06
    POSITIVE LOGITS
     aromatic
    0.09
    ionic
    0.07
    」↵
    0.07
     establishing
    0.06
     vendors
    0.06
    \"]
    0.06
     partnering
    0.06
    ')[
    0.06
    ưu
    0.06
    Really
    0.06
    Activations Density 0.016%

    No Known Activations