© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 20202
    Prev
    Next
    INDEX
    Explanations

    Technical documents and patents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _gender
    -0.06
     yummy
    -0.06
    .....
    -0.06
     назнач
    -0.06
     για
    -0.06
     nej
    -0.06
    zkum
    -0.06
     extras
    -0.06
    Grammar
    -0.06
    _KHR
    -0.06
    POSITIVE LOGITS
     HttpStatus
    0.07
     jo
    0.06
     ninh
    0.06
    night
    0.06
     atroc
    0.06
    浴
    0.06
    setDescription
    0.06
    ór
    0.06
     mệnh
    0.06
    beginTransaction
    0.06
    Activations Density 0.021%

    No Known Activations