© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7048
    Prev
    Next
    INDEX
    Explanations

    taking things for granted

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of essential resources or necessities (like water, air, food, roofs, lungs) described as luxuries we take for granted until they’re gone.

    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
     Streets
    -0.07
    -Type
    -0.07
    �
    -0.07
    adores
    -0.06
    _PASS
    -0.06
    CREMENT
    -0.06
    Twenty
    -0.06
     Vista
    -0.06
     flyers
    -0.06
    ifers
    -0.06
    POSITIVE LOGITS
    なし
    0.06
     onFinish
    0.06
     bah
    0.06
    /q
    0.06
    &
    0.06
    らない
    0.06
    ческие
    0.06
    -members
    0.06
    网址
    0.06
     خارجی
    0.06
    Activations Density 0.030%

    No Known Activations