© 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. 56110
    Prev
    Next
    INDEX
    Explanations

    Recent

    np_max-act · gemini-2.0-flash

    This neuron identifies occurrences of the word “Recent” (as in “Recent studies/research”) signaling mentions of new or current research findings.

    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
     Remed
    -0.08
     команди
    -0.07
    ýš
    -0.06
    Normally
    -0.06
     Европ
    -0.06
     Flower
    -0.06
    LineNumber
    -0.06
     ermög
    -0.06
     membranes
    -0.06
    ildo
    -0.06
    POSITIVE LOGITS
     Recent
    0.08
    HN
    0.07
    Recent
    0.07
    ace
    0.07
     recent
    0.07
    hn
    0.07
    780
    0.06
    uien
    0.06
    СТ
    0.06
    ocs
    0.06
    Activations Density 0.012%

    No Known Activations