© 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. 54462
    Prev
    Next
    INDEX
    Explanations

    talking about everything

    np_max-act · gemini-2.0-flash

    This neuron detects lexical cues that introduce a broad range or enumeration—words like “wide,” “variety,” “of,” “subjects,” “various,” “topics,” and “from” that signal discussing a scope or list of items.

    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
    Balance
    -0.07
    riors
    -0.07
    �
    -0.06
    яви
    -0.06
    فی
    -0.06
    ект
    -0.06
     insist
    -0.06
    intro
    -0.06
     برخی
    -0.06
    ственно
    -0.06
    POSITIVE LOGITS
     alertDialog
    0.07
     Mandal
    0.07
    /packages
    0.07
    imuth
    0.07
    .getBounds
    0.06
    npj
    0.06
    .Target
    0.06
     datePicker
    0.06
    persist
    0.06
     mah
    0.06
    Activations Density 0.054%

    No Known Activations