Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 88731
    Prev
    Next
    INDEX
    Explanations

    Hotel booking/reservations

    np_max-act · gemini-2.0-flash

    information related to hotel reservations and related procedures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron identifies words related to hotel reservation and room‐block booking details (e.g., room, rate, cutoff date, deposit).

    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
     scalability
    -0.06
     tinder
    -0.06
    銷
    -0.06
     지원
    -0.06
    BUFF
    -0.06
    inizin
    -0.06
    encoded
    -0.05
     grew
    -0.05
    İ
    -0.05
    確認
    -0.05
    POSITIVE LOGITS
     граду
    0.07
     have
    0.07
     acum
    0.07
     vole
    0.07
    _xlabel
    0.06
    Cloud
    0.06
    objPHPExcel
    0.06
     Coleman
    0.06
    役
    0.06
     Trump
    0.06
    Activations Density 0.066%

    No Known Activations