© 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. 40973
    Prev
    Next
    INDEX
    Explanations

    best, top, favorites

    np_max-act · gemini-2.0-flash

    The neuron fires on high‐intensity qualifiers or superlative descriptors (e.g. “best,” “most,” “talented,” “serious,” “top”).

    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
     Iss
    -0.07
    にして
    -0.07
    ('.');↵
    -0.06
     Spect
    -0.06
     zost
    -0.06
    ・・
    -0.06
    Maximum
    -0.06
    符
    -0.06
     thats
    -0.06
     espect
    -0.06
    POSITIVE LOGITS
    sanız
    0.07
    .DataAnnotations
    0.07
    _CLEAR
    0.07
     overwhel
    0.07
    Null
    0.06
     khắc
    0.06
    .IntPtr
    0.06
     wasm
    0.06
    .VideoCapture
    0.06
    cce
    0.06
    Activations Density 0.106%

    No Known Activations