© 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. 46145
    Prev
    Next
    INDEX
    Explanations

    warring families/houses

    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
     Fra
    -0.08
     Santa
    -0.07
    Patrick
    -0.07
     watt
    -0.07
     condom
    -0.06
     Κο
    -0.06
     Conrad
    -0.06
    吹
    -0.06
    deps
    -0.06
    園
    -0.06
    POSITIVE LOGITS
    	RTLU
    0.07
    ISE
    0.06
    .optString
    0.06
    (tag
    0.06
     afect
    0.06
    suppress
    0.06
    .router
    0.06
    (isset
    0.06
    .Math
    0.06
    ofi
    0.06
    Activations Density 0.006%

    No Known Activations