© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30172
    Prev
    Next
    INDEX
    Explanations

    scientific measurements

    np_max-act · gemini-2.0-flash

    The neuron detects numeric expressions specifying the “linear range” (i.e., calibration or measurement range) in analytical method descriptions.

    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
    adle
    -0.07
     Kam
    -0.06
    리그
    -0.06
     K
    -0.06
    Merit
    -0.06
    	Gtk
    -0.06
     ASM
    -0.06
     TEM
    -0.06
     Char
    -0.06
     spre
    -0.06
    POSITIVE LOGITS
    ส
    0.06
    ,message
    0.06
     말을
    0.06
    الت
    0.06
    loit
    0.06
     lado
    0.06
    (group
    0.06
     Petty
    0.06
    不同的
    0.06
    นส
    0.06
    Activations Density 0.006%

    No Known Activations