© 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. 58207
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects repeated occurrences of the phrase “nature of the.”

    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
    189
    -0.07
     Elder
    -0.06
    콩
    -0.06
    paRepository
    -0.06
    188
    -0.06
    ۰
    -0.06
     supermarket
    -0.06
     Cộng
    -0.06
     Slam
    -0.06
     tablespoons
    -0.06
    POSITIVE LOGITS
     nature
    0.10
     description
    0.08
     Nature
    0.07
    形
    0.07
    重
    0.07
     amenities
    0.07
     natur
    0.07
    (Type
    0.07
    About
    0.07
    ความร
    0.07
    Activations Density 0.014%

    No Known Activations