© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38244
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron detects blog‐style metadata and comment‐section markers (e.g. “.post,” “Comments,” timestamps, “on,” author/profile tokens).

    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
     روح
    -0.06
    Tester
    -0.06
     tren
    -0.06
    ést
    -0.06
     gön
    -0.06
     каш
    -0.06
     ве
    -0.06
    DEM
    -0.06
    unk
    -0.06
    σί
    -0.06
    POSITIVE LOGITS
    кої
    0.07
    лика
    0.07
    ика
    0.07
    рощ
    0.06
    ẩm
    0.06
     Puppy
    0.06
     Partisi
    0.06
     distilled
    0.06
    	want
    0.06
    !↵
    0.06
    Activations Density 0.005%

    No Known Activations