© 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. 54381
    Prev
    Next
    INDEX
    Explanations

    general text/dialogue

    np_max-act · gemini-2.0-flash

    This neuron identifies the “Thought” markers that introduce internal reasoning steps in the chain-of-thought format.

    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
     desk
    -0.07
    י
    -0.07
     coloring
    -0.06
    ABCDEFGHIJKLMNOP
    -0.06
    ारक
    -0.06
    remium
    -0.06
    (TimeSpan
    -0.06
     lugares
    -0.06
    loor
    -0.06
     objectId
    -0.06
    POSITIVE LOGITS
    owany
    0.07
    하세요
    0.06
     Παρ
    0.06
     ortaya
    0.06
     Hos
    0.06
     artery
    0.06
     aph
    0.06
     Cao
    0.06
    -aos
    0.06
     Lucas
    0.06
    Activations Density 0.001%

    No Known Activations