© 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. 9087
    Prev
    Next
    INDEX
    Explanations

    Chemical elements

    np_max-act · gemini-2.0-flash

    information related to the properties and structures of nanomaterials.

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

    The main thing this neuron does is detect mentions of chemical element symbols and atomic species (e.g., “Ti,” “Li,” “O”) in the text.

    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
    υπ
    -0.07
    *p
    -0.06
     zombies
    -0.06
    カ
    -0.06
    inet
    -0.06
     coronary
    -0.06
     vehement
    -0.06
     Playoff
    -0.06
     tantra
    -0.06
    nyder
    -0.06
    POSITIVE LOGITS
    (AP
    0.07
    {_
    0.07
    WHITE
    0.07
     Jasper
    0.06
     famous
    0.06
     consenting
    0.06
    >,</
    0.06
     &$
    0.06
    AGMENT
    0.06
    \\.
    0.06
    Activations Density 0.016%

    No Known Activations