© 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. 89316
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron activates on the “bibliography:” label (and related tokens) in document metadata, i.e. it detects bibliography field entries.

    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
     Pand
    -0.07
     Lump
    -0.07
     Kar
    -0.07
     Cruise
    -0.06
     Fit
    -0.06
     GET
    -0.06
     notify
    -0.06
     Carter
    -0.06
    .Tag
    -0.06
    .valueOf
    -0.06
    POSITIVE LOGITS
    .accessToken
    0.07
     vẫn
    0.06
    onestly
    0.06
     grupo
    0.06
    ();?>
    0.06
    .InnerText
    0.06
     practices
    0.06
     Evet
    0.06
     suffered
    0.06
    的情况
    0.06
    Activations Density 0.000%

    No Known Activations