© 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. 31032
    Prev
    Next
    INDEX
    Explanations

    Scientific/medical texts

    np_max-act · gemini-2.0-flash

    The neuron detects fragments of multi-part uppercase technical acronyms or abbreviations (e.g. SC-MWNTs, mp-MRI, VHr-HCC, hWJ-MSCs).

    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
    grades
    -0.07
     chipset
    -0.07
    .Range
    -0.06
     DF
    -0.06
     Scor
    -0.06
    Jos
    -0.06
     LF
    -0.06
     يد
    -0.06
    러리
    -0.06
    RB
    -0.06
    POSITIVE LOGITS
     brainstorm
    0.07
    сутств
    0.07
     UIScrollView
    0.06
    [label
    0.06
     střed
    0.06
    .parsers
    0.06
    рап
    0.06
     Computers
    0.06
    Firstname
    0.06
     adjusts
    0.06
    Activations Density 0.052%

    No Known Activations