© 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. 27997
    Prev
    Next
    INDEX
    Explanations

    2

    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
     zahrn
    -0.07
    _ov
    -0.06
     vám
    -0.06
    .urlopen
    -0.06
     adventurous
    -0.06
    (dx
    -0.06
     thấp
    -0.06
    งแรก
    -0.06
     madde
    -0.06
     percent
    -0.06
    POSITIVE LOGITS
     console
    0.06
     Celtics
    0.06
     Gobierno
    0.06
    оит
    0.06
    Trial
    0.05
    ічні
    0.05
    colors
    0.05
    许
    0.05
    	trace
    0.05
     κο
    0.05
    Activations Density 0.001%

    No Known Activations