© 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. 58426
    Prev
    Next
    INDEX
    Explanations

    refrigeration systems

    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
    .findBy
    -0.07
    JECTION
    -0.07
    warnings
    -0.07
    yy
    -0.07
    	This
    -0.06
    browse
    -0.06
     into
    -0.06
     Tabs
    -0.06
     explosive
    -0.06
    Modifier
    -0.06
    POSITIVE LOGITS
     Bilim
    0.07
     wom
    0.07
     rodin
    0.06
     dokon
    0.06
     overlook
    0.06
    .Controllers
    0.06
     envi
    0.06
    amura
    0.06
     nar
    0.06
    =open
    0.06
    Activations Density 0.028%

    No Known Activations