© 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. 126042
    Prev
    Next
    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash

    This neuron detects Portuguese security-related terms (e.g. “segurança,” “medidas de segurança,” “ferramentas de segurança”).

    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
    Leaks
    -0.07
    "For
    -0.07
     Ferry
    -0.06
    eatures
    -0.06
    jandro
    -0.06
    acons
    -0.06
     util
    -0.06
    láda
    -0.06
     ent
    -0.06
    ination
    -0.06
    POSITIVE LOGITS
     وضعیت
    0.07
     zvyš
    0.07
    ­n
    0.07
     stretch
    0.07
     interval
    0.07
    ba
    0.06
     excessive
    0.06
    ้ง
    0.06
    年的
    0.06
     portfolio
    0.06
    Activations Density 0.047%

    No Known Activations