© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129774
    Prev
    Next
    INDEX
    Explanations

    Travel experiences

    np_max-act · gemini-2.0-flash

    This neuron fires on the action‐item phrases in travel itineraries (e.g. “Have lunch…,” “In the afternoon…,” “End the day with…”).

    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
     vua
    -0.08
    OPER
    -0.07
    conexion
    -0.07
     xong
    -0.07
     zákon
    -0.06
     backend
    -0.06
     comparative
    -0.06
     Ed
    -0.06
     Kai
    -0.06
    EditingController
    -0.06
    POSITIVE LOGITS
    śli
    0.08
    ^(
    0.07
     Called
    0.06
    รณ
    0.06
     ارتف
    0.06
    径
    0.06
     bom
    0.06
    OUSE
    0.06
     cris
    0.06
    \Bundle
    0.06
    Activations Density 0.013%

    No Known Activations