© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55909
    Prev
    Next
    INDEX
    Explanations

    stations/venues

    np_max-act · gemini-2.0-flash

    The neuron detects Wikipedia category labels (the “Category:” lines) at the ends of articles.

    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
     کمتر
    -0.07
     바로
    -0.07
     아직
    -0.07
    .ComponentPlacement
    -0.06
    @Resource
    -0.06
    itles
    -0.06
    ’autres
    -0.06
     hotline
    -0.06
    osit
    -0.06
     Sans
    -0.06
    POSITIVE LOGITS
     Industries
    0.06
     license
    0.06
     teamed
    0.06
    ouncements
    0.06
     Constant
    0.06
     unified
    0.06
     departure
    0.06
    ORD
    0.06
     fearless
    0.06
    .detectChanges
    0.06
    Activations Density 0.013%

    No Known Activations