© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 66789
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on instructional or explanatory discourse markers—that is, words signaling that the text is giving directions, comparisons, examples, or conceptual explanations.

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

    references to open-source software systems used for automation.

    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
     },
    -0.07
     στο
    -0.06
     engr
    -0.06
    ocracy
    -0.06
     ειδ
    -0.06
     nr
    -0.06
     Auch
    -0.06
    inst
    -0.06
    place
    -0.06
    _);
    ↵
    -0.06
    POSITIVE LOGITS
     král
    0.07
    _usr
    0.07
     getUsers
    0.06
     miscon
    0.06
     معرف
    0.06
      			
    0.06
     ','.
    0.06
    فر
    0.06
     setattr
    0.06
    Program
    0.06
    Activations Density 0.066%

    No Known Activations