© 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. 68499
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires on the special “angle‐bar” formatting tokens and other metadata markers (e.g. <|begin_of_text|>, <|start_header_id|>, 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
    ovky
    -0.06
    írk
    -0.06
    ест
    -0.06
    untime
    -0.06
    roker
    -0.06
    τικών
    -0.06
    น
    -0.06
    sembler
    -0.06
     enhancement
    -0.06
     Ui
    -0.05
    POSITIVE LOGITS
    >.↵
    0.07
    /)↵
    0.07
    Former
    0.07
    .facebook
    0.06
     рассчит
    0.06
    Partial
    0.06
    County
    0.06
     Spiritual
    0.06
    series
    0.06
    );?>↵
    0.06
    Activations Density 0.045%

    No Known Activations