© 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. 91317
    Prev
    Next
    INDEX
    Explanations

    Sentence beginnings

    np_max-act · gemini-2.0-flash

    The neuron detects third-person singular present-tense action verbs (verbs ending in “s” like “comes,” “stands,” “tries,” “continues,” etc.).

    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
    mix
    -0.07
    (bits
    -0.07
    .ReadToEnd
    -0.07
    arakter
    -0.06
     bearing
    -0.06
     GPS
    -0.06
    坪
    -0.06
    _factors
    -0.06
     ấy
    -0.06
    一种
    -0.06
    POSITIVE LOGITS
    ซ
    0.06
    _USB
    0.06
     Repo
    0.06
     MW
    0.06
     Lac
    0.06
    .But
    0.06
    ,row
    0.06
     مغ
    0.06
     Alaska
    0.06
     Montana
    0.06
    Activations Density 0.072%

    No Known Activations