© 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. 635
    Prev
    Next
    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of “http” as part of documentation URLs (e.g., “http://…”) in code comments.

    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
    subscriber
    -0.07
     있도록
    -0.06
     lifespan
    -0.06
     favicon
    -0.06
    (dec
    -0.06
    ующий
    -0.06
    BUS
    -0.06
    -night
    -0.06
    ัพท
    -0.06
     Edgar
    -0.06
    POSITIVE LOGITS
    getAttribute
    0.06
    pread
    0.06
     결혼
    0.06
     конкрет
    0.06
     енерг
    0.06
     факти
    0.06
     },↵↵↵
    0.06
     ход
    0.06
    hg
    0.06
    џџџџџџџџџџџџџџџџ
    0.06
    Activations Density 0.008%

    No Known Activations