© 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. 74642
    Prev
    Next
    INDEX
    Explanations

    First in the world

    np_max-act · gemini-2.0-flash

    references to initiatives and structures related to renewable energy and environmental sustainability.

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

    This neuron responds to words and phrases signaling primacy or novelty—especially “first,” “first in (the) nation/world,” and “of its kind.”

    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
     allev
    -0.07
    gap
    -0.07
    angel
    -0.07
    /hooks
    -0.06
     pulls
    -0.06
    abo
    -0.06
    goal
    -0.06
    Didn
    -0.06
    _Height
    -0.06
    HD
    -0.06
    POSITIVE LOGITS
    ERA
    0.07
     cj
    0.07
    navbarDropdown
    0.07
     patched
    0.06
    odash
    0.06
    HasColumnType
    0.06
    ेम
    0.06
    cons
    0.06
     �
    0.06
    antly
    0.06
    Activations Density 0.013%

    No Known Activations