© 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. 130113
    Prev
    Next
    INDEX
    Explanations

    time or length

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of numeric quantities, measures, or durations (e.g. "one use," "a number of hours," "once per day").

    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
    ICES
    -0.07
    熊
    -0.07
    _called
    -0.07
    elems
    -0.07
    findBy
    -0.06
     folded
    -0.06
     belts
    -0.06
     इसस
    -0.06
    야
    -0.06
     больш
    -0.06
    POSITIVE LOGITS
     Р
    0.07
     Arabic
    0.07
     Prot
    0.07
    .Abstract
    0.07
    =”
    0.06
     Ke
    0.06
    _theme
    0.06
     =$
    0.06
     Ab
    0.06
    ultur
    0.06
    Activations Density 0.069%

    No Known Activations