© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126412
    Prev
    Next
    INDEX
    Explanations

    Role-playing context

    np_max-act · gemini-2.0-flash

    The neuron is triggered by out-of-character/meta instructions markers (e.g. “out of character,” bracket delimiters, “OOC,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aged
    -0.06
    -bold
    -0.06
     není
    -0.06
     literature
    -0.06
    وري
    -0.06
    ніше
    -0.06
    iệt
    -0.06
     düzenlenen
    -0.06
     Completed
    -0.06
    eh
    -0.06
    POSITIVE LOGITS
     Mercer
    0.07
    ingle
    0.07
    .LOG
    0.07
    ��
    0.07
    MB
    0.07
     rozhod
    0.06
     Qualcomm
    0.06
     Oswald
    0.06
     Dancing
    0.06
     Chat
    0.06
    Activations Density 0.014%

    No Known Activations