© 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. 90739
    Prev
    Next
    INDEX
    Explanations

    service

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to corporate value‐proposition wording—especially mentions of “quality” and “customer service.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    chemical companies that focus on high-quality products and sustainability.

    oai_token-act-pair · gpt-4o-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
     कल
    -0.07
    Regular
    -0.07
     RPC
    -0.07
    (prev
    -0.07
    exact
    -0.06
     Everyday
    -0.06
     getir
    -0.06
     Props
    -0.06
     distancing
    -0.06
     Wonderful
    -0.06
    POSITIVE LOGITS
     transporte
    0.07
    heiten
    0.06
    애
    0.06
    cano
    0.06
    ěj
    0.06
     fabrics
    0.06
     puede
    0.06
    ’d
    0.06
     بیمار
    0.06
    ेज
    0.06
    Activations Density 0.023%

    No Known Activations