© 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. 19-RESID-POST-AA
    6. 9995
    Prev
    Next
    INDEX
    Explanations

    variety of unrelated sources

    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
    ้องก
    -0.07
     Amen
    -0.06
     finely
    -0.06
    ویل
    -0.06
     chasing
    -0.06
     깨
    -0.06
    _prod
    -0.06
     followers
    -0.06
     consultants
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    =$
    0.07
     Lua
    0.07
    $ret
    0.07
     RuntimeException
    0.07
     ücret
    0.06
    ]:↵↵↵
    0.06
     nostalgia
    0.06
    /
    0.06
    ITS
    0.06
    ACEMENT
    0.06
    Activations Density 0.197%

    No Known Activations