© 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. 54274
    Prev
    Next
    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX-style reference markers, i.e. backslash-hash followed by a digit (e.g. “\#1”, “\#2”, etc.).

    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
     stří
    -0.06
     sức
    -0.06
     tul
    -0.06
    _npc
    -0.06
     фіз
    -0.06
     внутрен
    -0.06
     nabízí
    -0.06
    �
    -0.06
     ########################################################################
    -0.06
    .tif
    -0.06
    POSITIVE LOGITS
    polator
    0.08
    >-->↵
    0.08
    grab
    0.07
     Clash
    0.07
     *)↵
    0.07
     wrestling
    0.07
     northwest
    0.07
    /App
    0.07
     supplementation
    0.07
    because
    0.07
    Activations Density 0.002%

    No Known Activations