© 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. 15-RESID-POST-AA
    11. 115648
    Prev
    Next
    INDEX
    Explanations

    objectivity and neutrality

    np_max-act · gemini-2.0-flash

    mentions of political stance labels or classification outputs (e.g., dovish/neutral/hawkish and related label tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consequently
    -0.06
     Pollution
    -0.06
     waste
    -0.06
     Belle
    -0.06
     вона
    -0.06
    ४
    -0.06
     billeder
    -0.06
     extract
    -0.06
    Beam
    -0.06
    icut
    -0.06
    POSITIVE LOGITS
     nej
    0.07
     Watson
    0.07
     pud
    0.07
    /update
    0.06
    .InteropServices
    0.06
    是什么
    0.06
     fantast
    0.06
     PRES
    0.06
    ,void
    0.06
     иму
    0.06
    Activations Density 0.232%

    No Known Activations