© 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. 14058
    Prev
    Next
    INDEX
    Explanations

    repeating

    np_max-act · gemini-2.0-flash

    chemical compounds used as building blocks or intermediates in synthesis processes.

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

    This neuron specializes in detecting mentions of polysaccharide structure, particularly phrases describing repeating disaccharide (sugar) units.

    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
     Upload
    -0.08
     upload
    -0.07
     арх
    -0.07
    404
    -0.07
     scour
    -0.07
    聊
    -0.07
     prescription
    -0.07
     Zeus
    -0.07
    io
    -0.07
    備
    -0.06
    POSITIVE LOGITS
     cellForRowAtIndexPath
    0.06
    ═
    0.06
    .ac
    0.06
     阿
    0.06
    .ActionEvent
    0.06
    enzyme
    0.06
    .ticket
    0.06
    .Change
    0.05
     resembl
    0.05
     بط
    0.05
    Activations Density 0.008%

    No Known Activations