© 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. 3-RESID-POST-AA
    11. 93849
    Prev
    Next
    INDEX
    Explanations

    line

    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
    ьми
    -0.07
     orchestr
    -0.07
     Guardian
    -0.06
    ibbean
    -0.06
    ером
    -0.06
    ้าต
    -0.06
    (Photo
    -0.06
     maximizing
    -0.06
    ivia
    -0.06
    -man
    -0.06
    POSITIVE LOGITS
    protobuf
    0.12
    sl
    0.08
     ===>
    0.07
     MADE
    0.06
    lok
    0.06
    _TASK
    0.06
    필
    0.06
    _Static
    0.06
     Fist
    0.06
    �
    0.06
    Activations Density 0.002%

    No Known Activations