© 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
    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. 68622
    Prev
    Next
    INDEX
    Explanations

    Companies and technologies

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of specific grain or crop names (e.g., barley, corn, flax, oats, rye, soybeans).

    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
    vrd
    -0.08
    학회
    -0.06
     ng
    -0.06
    Since
    -0.06
     («
    -0.06
     technique
    -0.06
    Jean
    -0.06
     Since
    -0.06
    кор
    -0.06
     Angle
    -0.06
    POSITIVE LOGITS
     utan
    0.07
    chte
    0.06
    ность
    0.06
     firearm
    0.06
     deleteUser
    0.06
     gameTime
    0.06
     NHL
    0.06
    _STACK
    0.06
    .default
    0.06
    _city
    0.06
    Activations Density 0.090%

    No Known Activations