© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 40170
    Prev
    Next
    INDEX
    Explanations

    align

    np_max-act · gemini-2.0-flash

    regions of LaTeX/math markup (TeX commands, symbols, and display-math 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
    Roz
    -0.07
    .array
    -0.06
     náklad
    -0.06
    牛
    -0.06
     bee
    -0.06
     prest
    -0.06
     tariffs
    -0.06
     todas
    -0.06
     更
    -0.06
    Expansion
    -0.06
    POSITIVE LOGITS
    ользов
    0.07
     LoginForm
    0.06
    ธ
    0.06
    劇
    0.06
     فضای
    0.06
    io
    0.06
    χα
    0.06
     unexpected
    0.06
    ipers
    0.06
    .vm
    0.06
    Activations Density 0.001%

    No Known Activations