© 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. 89773
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on the assistant’s own self-descriptive or “meta” language—tokens appearing when it’s talking about its capabilities, services, or internal behavior.

    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
    Dev
    -0.07
    arshal
    -0.06
    	speed
    -0.06
     eens
    -0.06
     ki
    -0.06
    ци
    -0.06
    .opts
    -0.06
    Expired
    -0.06
    optim
    -0.06
    ям
    -0.06
    POSITIVE LOGITS
     swirling
    0.06
    AVE
    0.06
    FORMATION
    0.06
     shimmer
    0.06
    _tb
    0.06
    ighting
    0.06
     rozhod
    0.06
     Ao
    0.06
    cp
    0.06
     สามารถ
    0.06
    Activations Density 0.148%

    No Known Activations