© 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 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. 57298
    Prev
    Next
    INDEX
    Explanations

    detailed

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on occurrences of the word “detailed.”

    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
     Browns
    -0.07
     off
    -0.07
    ucs
    -0.07
    aviours
    -0.06
     sopr
    -0.06
     کاهش
    -0.06
     offs
    -0.06
     hosts
    -0.06
    ukes
    -0.06
     Off
    -0.06
    POSITIVE LOGITS
     detailed
    0.13
    ized
    0.08
    Detailed
    0.08
     realistic
    0.07
     Detailed
    0.07
    ARED
    0.07
     vivid
    0.07
    D
    0.07
     Fuller
    0.07
    UTE
    0.07
    Activations Density 0.016%

    No Known Activations