© 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. 124939
    Prev
    Next
    INDEX
    Explanations

    </

    np_max-act · gemini-2.0-flash

    The neuron detects the beginning of HTML/XML closing‐tag sequences (i.e. the “</” token).

    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
    ignum
    -0.07
     //-
    -0.06
     nuis
    -0.06
     OPS
    -0.06
    振り
    -0.06
     mimo
    -0.06
    ALT
    -0.06
    halten
    -0.06
    EI
    -0.06
     Opr
    -0.06
    POSITIVE LOGITS
    西
    0.07
     getTitle
    0.07
     ₹
    0.07
     ammunition
    0.06
     Ав
    0.06
    _sentence
    0.06
    |#
    0.06
     gd
    0.06
     phẩm
    0.06
    getUser
    0.06
    Activations Density 0.003%

    No Known Activations