© 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. 117870
    Prev
    Next
    INDEX
    Explanations

    Drifting on water

    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
    Tyler
    -0.07
     planets
    -0.06
    Bonjour
    -0.06
     Bij
    -0.06
     retVal
    -0.06
     �
    -0.06
    部门
    -0.06
    خم
    -0.06
     /
    -0.06
    Plant
    -0.05
    POSITIVE LOGITS
    .SelectCommand
    0.07
     elgg
    0.07
     drift
    0.06
    .Modified
    0.06
     componentWill
    0.06
    XX
    0.06
    	writel
    0.06
    ;;
    0.06
     срав
    0.06
    .INPUT
    0.06
    Activations Density 0.043%

    No Known Activations