© 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. 44459
    Prev
    Next
    INDEX
    Explanations

    "/>

    np_max-act · gemini-2.0-flash

    The neuron is triggered by XML/HTML tags that immediately close themselves (i.e. self-closing tags like `<tag …/>`).

    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
    _mean
    -0.07
    _dec
    -0.07
     xe
    -0.07
    è
    -0.07
     é
    -0.07
     mse
    -0.07
     de
    -0.07
    'e
    -0.07
     es
    -0.07
     ce
    -0.06
    POSITIVE LOGITS
     robert
    0.08
    MAP
    0.08
    .'/'.$
    0.08
    "/>↵
    0.07
    ิ่
    0.07
    '/>
    0.07
     listop
    0.07
     eskorte
    0.07
    isp
    0.07
    _cutoff
    0.07
    Activations Density 0.012%

    No Known Activations