© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 123366
    Prev
    Next
    INDEX
    Explanations

    pe

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [@
    -0.07
    日期
    -0.07
    .number
    -0.06
     ex
    -0.06
    。在
    -0.06
     obvious
    -0.06
    _fm
    -0.06
    ntax
    -0.06
     tax
    -0.06
     surpr
    -0.06
    POSITIVE LOGITS
    공지
    0.09
     Consultants
    0.07
    /copyleft
    0.07
    ково
    0.07
    ��
    0.07
    lamaktadır
    0.07
     �
    0.07
     topo
    0.07
     Pope
    0.07
     PIT
    0.07
    Activations Density 0.003%

    No Known Activations