© 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. 14069
    Prev
    Next
    INDEX
    Explanations

    different, unique

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases that express quantities or counts (e.g. numbers and quantifiers like “a bunch,” “lots,” or “twelve”).

    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
     emacs
    -0.06
     télé
    -0.06
     Bac
    -0.06
    young
    -0.06
    _teacher
    -0.06
    Sony
    -0.06
    좋
    -0.06
    Aliases
    -0.06
    _NONNULL
    -0.06
    ального
    -0.06
    POSITIVE LOGITS
    Ě
    0.07
    .General
    0.07
     '=',
    0.07
    为空
    0.07
     quad
    0.07
     Drake
    0.07
     getWindow
    0.06
     iliş
    0.06
     đêm
    0.06
     pesso
    0.06
    Activations Density 0.026%

    No Known Activations