© 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. 39034
    Prev
    Next
    INDEX
    Explanations

    This

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “This,” especially when it begins a sentence or text segment.

    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
     payloads
    -0.07
    	rd
    -0.06
     늘
    -0.06
     Также
    -0.06
    lers
    -0.06
     resumed
    -0.06
     attribution
    -0.06
     Revel
    -0.06
     pounds
    -0.06
    IRECT
    -0.06
    POSITIVE LOGITS
    This
    0.10
     This
    0.09
     this
    0.08
    "This
    0.08
    Duration
    0.07
     być
    0.07
     neste
    0.07
    _ne
    0.06
    theta
    0.06
    imals
    0.06
    Activations Density 0.003%

    No Known Activations