© 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. 92622
    Prev
    Next
    INDEX
    Explanations

    now are

    np_max-act · gemini-2.0-flash

    This neuron detects role‐assignment prompts, specifically the phrase pattern “you are now …” that sets a new persona or role.

    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
     Marc
    -0.06
     assistir
    -0.06
    TextLabel
    -0.06
    .long
    -0.06
    <decimal
    -0.06
     slipping
    -0.06
    Lin
    -0.06
     màn
    -0.06
     Among
    -0.06
    Marc
    -0.06
    POSITIVE LOGITS
     хвор
    0.08
    abee
    0.07
    βε
    0.07
     dubna
    0.07
     marshaller
    0.07
    ję
    0.06
     mate
    0.06
     Situation
    0.06
    чні
    0.06
     ilaç
    0.06
    Activations Density 0.009%

    No Known Activations