© 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. 56071
    Prev
    Next
    INDEX
    Explanations

    .desktop files

    np_max-act · gemini-2.0-flash

    The neuron is detecting references to Linux desktop‐entry (“.desktop”) launcher files and their configuration fields.

    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
     Priest
    -0.08
    	ui
    -0.06
     Wimbledon
    -0.06
    house
    -0.06
    姑
    -0.06
     ende
    -0.06
     Mon
    -0.06
    .tt
    -0.06
    (guess
    -0.06
    Shield
    -0.06
    POSITIVE LOGITS
     braz
    0.06
    approval
    0.06
    عام
    0.06
    nonatomic
    0.06
     männer
    0.06
     kamu
    0.06
    mostat
    0.06
    ρωπα
    0.06
    pci
    0.06
    oglob
    0.06
    Activations Density 0.007%

    No Known Activations