© 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. 44147
    Prev
    Next
    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash

    This neuron is tuned to detect technical engine specification details, especially numeric displacement values and engine type identifiers (e.g. “V8,” “small‐block,” “350”).

    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
    CartItem
    -0.07
     harga
    -0.06
    Senha
    -0.06
    _points
    -0.06
    Pixels
    -0.06
     zd
    -0.06
    retrieve
    -0.06
     �
    -0.06
    Business
    -0.06
    ALL
    -0.06
    POSITIVE LOGITS
    (PDO
    0.07
     Guzzle
    0.07
     "{$
    0.07
     lawsuit
    0.07
     @{$
    0.07
     tidak
    0.06
    도록
    0.06
     выдел
    0.06
    	sound
    0.06
     Sham
    0.06
    Activations Density 0.005%

    No Known Activations