© 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 EvalsExportsAPI 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. 57299
    Prev
    Next
    INDEX
    Explanations

    install

    np_max-act · gemini-2.0-flash

    commands related to code installation and configurations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on occurrences of “install” (and its variants) in command‐instruction contexts.

    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
     бума
    -0.07
    .stop
    -0.07
    mans
    -0.06
    .usage
    -0.06
    von
    -0.06
    learner
    -0.06
     IAM
    -0.06
     wat
    -0.06
    it
    -0.06
    iễn
    -0.06
    POSITIVE LOGITS
     طریق
    0.06
     Strong
    0.06
     hå
    0.06
     clang
    0.06
     أجل
    0.06
     зависит
    0.06
    ;}
    0.06
    _Local
    0.06
    DockControl
    0.06
    Backdrop
    0.06
    Activations Density 0.005%

    No Known Activations