© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 29901
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    tokens belonging to the assistant's reply (i.e., text from the assistant speaker/assistant turn).

    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
     ứng
    -0.06
    .authService
    -0.06
    γ
    -0.06
    ,np
    -0.06
    aspect
    -0.06
    '})↵
    -0.06
    -q
    -0.06
     Boyd
    -0.06
    .cx
    -0.06
    scheme
    -0.06
    POSITIVE LOGITS
     Ord
    0.06
     lign
    0.06
    (HWND
    0.06
    �
    0.06
     parsed
    0.06
     Organ
    0.06
     aconte
    0.06
    ifetime
    0.06
     spans
    0.06
     окрем
    0.06
    Activations Density 0.799%

    No Known Activations