© 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 EvalsExportsinterp-engineNEWAPI 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. 58166
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron flags common function words—especially prepositions and articles like “to,” “the,” “from,” and “an.”

    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
    Empresa
    -0.07
    ioctl
    -0.07
    _trap
    -0.06
     Incre
    -0.06
     açısından
    -0.06
     secretive
    -0.06
     Перед
    -0.06
     durante
    -0.06
    _organization
    -0.06
     又
    -0.06
    POSITIVE LOGITS
    mount
    0.06
    .examples
    0.06
    .vn
    0.06
     限
    0.06
     singles
    0.06
    lications
    0.06
     padding
    0.06
     contentValues
    0.06
    .addObserver
    0.06
    actices
    0.06
    Activations Density 0.127%

    No Known Activations