© 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. 129950
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron is picking out high‐frequency “glue” tokens—common function words (and sentence punctuation like periods) that mark sentence boundaries or transitions—rather than content words.

    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
     estimator
    -0.07
    حد
    -0.07
     Fountain
    -0.06
     effects
    -0.06
    K
    -0.06
    Apparently
    -0.06
     chatting
    -0.06
     Sunshine
    -0.06
    Quantity
    -0.06
    .$
    -0.06
    POSITIVE LOGITS
     infamous
    0.07
    Tools
    0.06
     brows
    0.06
     suffer
    0.06
    .addData
    0.06
    ‌ب
    0.06
     Maurit
    0.06
    _attrib
    0.06
     mies
    0.06
    _CONF
    0.06
    Activations Density 0.045%

    No Known Activations