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. 129302
    Prev
    Next
    INDEX
    Explanations

    Shifting data

    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
     komb
    -0.06
     HM
    -0.06
    .decorate
    -0.06
     ゝ
    -0.06
    �이
    -0.06
    /help
    -0.06
     граф
    -0.06
    .SizeType
    -0.06
    COPE
    -0.06
     temel
    -0.05
    POSITIVE LOGITS
     overclock
    0.08
    located
    0.07
    .↵↵
    0.07
     amended
    0.07
    jev
    0.06
     příspě
    0.06
     differs
    0.06
    _kernel
    0.06
    rition
    0.06
     asserts
    0.06
    Activations Density 0.030%

    No Known Activations