© 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. 68506
    Prev
    Next
    INDEX
    Explanations

    negative words

    np_max-act · gemini-2.0-flash

    The neuron activates on phrases where the assistant states it “does not have” or “cannot” possess or access something, marking expressions of inability or lack.

    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
    _EMPTY
    -0.07
    HasBeenSet
    -0.07
     Thumbnail
    -0.07
    .training
    -0.07
    pped
    -0.06
     kids
    -0.06
     Authority
    -0.06
     کد
    -0.06
    यन
    -0.06
    .save
    -0.06
    POSITIVE LOGITS
     giấy
    0.06
    _nth
    0.06
    _di
    0.06
    lol
    0.06
    idx
    0.06
    (ns
    0.06
    ايد
    0.06
     {:.
    0.06
    ).^
    0.05
    isol
    0.05
    Activations Density 0.022%

    No Known Activations