© 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. 57231
    Prev
    Next
    INDEX
    Explanations

    verify

    np_max-act · gemini-2.0-flash

    The neuron detects imperative verbs that introduce procedural steps (e.g. “Find,” “Verify”) in instruction sequences.

    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
    (Input
    -0.07
    ель
    -0.07
     Sonic
    -0.07
     Sentence
    -0.06
     Jonas
    -0.06
    avirus
    -0.06
    .Menu
    -0.06
     Đức
    -0.06
     Kurdistan
    -0.06
    doc
    -0.06
    POSITIVE LOGITS
     Poly
    0.06
    _pieces
    0.06
     flexible
    0.06
    范围
    0.06
     Mö
    0.06
     přev
    0.06
     Pri
    0.06
    OLUMNS
    0.06
    .xhtml
    0.06
     nepř
    0.06
    Activations Density 0.012%

    No Known Activations