© 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. 128348
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    The neuron activates on comparative or superlative degree words (e.g. “more,” “less,” “most,” “relatively”) indicating relative comparisons.

    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
    伟
    -0.07
     prise
    -0.06
     Brigade
    -0.06
     weer
    -0.06
     math
    -0.06
     adorned
    -0.06
    ensaje
    -0.06
     če
    -0.06
     Alec
    -0.06
    	pp
    -0.06
    POSITIVE LOGITS
    abb
    0.06
     EXPRESS
    0.06
    (startDate
    0.06
    _AUDIO
    0.06
     postal
    0.06
    .swt
    0.06
     defin
    0.06
     comple
    0.06
     superf
    0.06
    /header
    0.06
    Activations Density 0.164%

    No Known Activations