© 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. 5881
    Prev
    Next
    INDEX
    Explanations

    000

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens consisting of three zeros (“000”), i.e. the “000” parts of large round numbers.

    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
     dart
    -0.06
    �
    -0.06
    41
    -0.06
     ie
    -0.06
    plt
    -0.06
     sf
    -0.06
     hôm
    -0.06
    6
    -0.06
    毕
    -0.06
     ain
    -0.06
    POSITIVE LOGITS
    000
    0.10
     QU
    0.09
     POW
    0.08
    (Key
    0.08
    OW
    0.08
     DateTimeKind
    0.08
    ow
    0.07
     owns
    0.07
     thousands
    0.07
    ODO
    0.07
    Activations Density 0.030%

    No Known Activations