© 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. 126630
    Prev
    Next
    INDEX
    Explanations

    Michelin restaurants

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of fine‐dining restaurants marked by Michelin (and related star ratings) — i.e. references to “gourmet” establishments, “restaurant,” and “Michelin.”

    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
    Lista
    -0.06
    .onSubmit
    -0.06
     Consult
    -0.06
     Deadpool
    -0.06
    ظ
    -0.06
    .Parse
    -0.06
    edula
    -0.06
     bankruptcy
    -0.06
    %%%%%%%%
    -0.06
    ��드
    -0.06
    POSITIVE LOGITS
    .parsers
    0.06
    mitter
    0.06
    .addField
    0.06
     statist
    0.06
    verbs
    0.06
    mill
    0.06
     Blue
    0.06
     containment
    0.06
     стала
    0.06
    -HT
    0.06
    Activations Density 0.025%

    No Known Activations