© 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. 112019
    Prev
    Next
    INDEX
    Explanations

    instructions and procedures

    np_max-act · gemini-2.0-flash

    sentences or phrases that give step-by-step instructions or procedural guidance, especially for emergency/safety responses.

    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
    .tex
    -0.08
     som
    -0.07
     tối
    -0.07
     nichž
    -0.07
    КИ
    -0.07
     багатьох
    -0.07
     uğ
    -0.07
    НО
    -0.07
    .cuda
    -0.07
    帕
    -0.07
    POSITIVE LOGITS
    обыти
    0.06
     urges
    0.06
    (enc
    0.05
     Marseille
    0.05
     misled
    0.05
     bookstore
    0.05
     Andr
    0.05
     retailer
    0.05
    yalty
    0.05
     Vintage
    0.05
    Activations Density 0.068%

    No Known Activations