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

    Neuronpedia

    Jacobian LensNEW
    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. 20931
    Prev
    Next
    INDEX
    Explanations

    Addressing or handling

    np_max-act · gemini-2.0-flash

    phrases asking about plans, policies, or how to deal with / take action on something.

    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
     ซ
    -0.07
    translate
    -0.07
     dal
    -0.07
     Nhân
    -0.07
    イス
    -0.06
    tar
    -0.06
    brief
    -0.06
    mam
    -0.06
     stru
    -0.06
    boru
    -0.06
    POSITIVE LOGITS
    .md
    0.06
     scary
    0.06
    ических
    0.06
    .optString
    0.06
    .Authentication
    0.06
    วไป
    0.06
    .Component
    0.06
     ConcurrentHashMap
    0.06
    _md
    0.06
    你们
    0.06
    Activations Density 0.255%

    No Known Activations