© 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. 19-RESID-POST-AA
    11. 87891
    Prev
    Next
    INDEX
    Explanations

    140

    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
     Live
    -0.07
    setData
    -0.07
     Dante
    -0.07
     rights
    -0.07
    bindParam
    -0.06
     доч
    -0.06
     granite
    -0.06
    ismatch
    -0.06
    	Function
    -0.06
    andal
    -0.06
    POSITIVE LOGITS
    739
    0.07
    HAS
    0.07
     awaken
    0.07
     şans
    0.07
     Skin
    0.07
    xl
    0.06
    740
    0.06
     attack
    0.06
    541
    0.06
    开始
    0.06
    Activations Density 0.011%

    No Known Activations