© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129960
    Prev
    Next
    INDEX
    Explanations

    visual

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of “visual” (and related neuroscience terms like visual cortex or visual stimulation) in scientific text.

    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
     Eaton
    -0.07
     Gingrich
    -0.07
    gpu
    -0.06
     mh
    -0.06
     Partition
    -0.06
     condem
    -0.06
    Descriptors
    -0.06
     Gran
    -0.06
     disple
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     At
    0.07
    522
    0.07
    -des
    0.06
     auditory
    0.06
    イス
    0.06
    getElement
    0.06
    -div
    0.06
    getId
    0.06
    urally
    0.06
     тип
    0.06
    Activations Density 0.008%

    No Known Activations