© 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. 16006
    Prev
    Next
    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash

    mentions of chatbots and conversational AI topics (dialogue, training/deployment, and related instructional steps).

    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
    他們
    -0.07
    aktu
    -0.07
    olvency
    -0.06
     therapies
    -0.06
     compel
    -0.06
    ремя
    -0.06
    اسه
    -0.06
    into
    -0.06
     protože
    -0.06
     zijn
    -0.06
    POSITIVE LOGITS
     Published
    0.06
     Sistem
    0.06
    Defines
    0.06
    employed
    0.06
     форм
    0.06
     Pessoa
    0.06
     Petsc
    0.06
    .invoke
    0.06
    INCREMENT
    0.06
     Phot
    0.06
    Activations Density 0.086%

    No Known Activations