© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129576
    Prev
    Next
    INDEX
    Explanations

    Trucks

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of specific software, tools, libraries, or technical product names.

    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
     LPARAM
    -0.07
     upto
    -0.07
    ">{{
    -0.07
    vail
    -0.06
    _JS
    -0.06
    	afx
    -0.06
     myfile
    -0.06
    :%
    -0.06
     THREAD
    -0.06
     FileStream
    -0.06
    POSITIVE LOGITS
    .Void
    0.06
     Орг
    0.06
    egr
    0.06
    育
    0.06
    ulence
    0.06
    opsy
    0.06
    -‐
    0.06
    oplan
    0.06
    akeup
    0.05
     조교
    0.05
    Activations Density 0.029%

    No Known Activations