© 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. 40933
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of “continues to …” (and similar “demand continues to…,” “grow,” “rise,” “increase,” etc.)—i.e. phrases expressing ongoing growth or increase.

    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
     Czech
    -0.06
    osy
    -0.06
    емых
    -0.06
    .isPlaying
    -0.06
    ading
    -0.06
     Buy
    -0.06
     west
    -0.06
     moreover
    -0.06
     termed
    -0.06
     работу
    -0.05
    POSITIVE LOGITS
    정이
    0.07
    琳
    0.07
    ้อง
    0.06
    IMO
    0.06
    VF
    0.06
    心
    0.06
     Hyper
    0.06
     Budapest
    0.06
    _QU
    0.06
     cord
    0.06
    Activations Density 0.015%

    No Known Activations