© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129767
    Prev
    Next
    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash

    This neuron detects numeric expressions, especially measurements or quantities given as numbers (including decimals and percentages).

    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
    :white
    -0.06
     rebell
    -0.06
    chor
    -0.06
     vocalist
    -0.06
     suppression
    -0.06
    ώσεις
    -0.06
     aktuální
    -0.06
     chees
    -0.06
    Du
    -0.06
     κό
    -0.06
    POSITIVE LOGITS
    	Path
    0.06
     ПО
    0.06
    ivicrm
    0.06
     países
    0.06
     nộp
    0.06
    	EIF
    0.06
     pozit
    0.06
     jenis
    0.06
     输出
    0.06
     غير
    0.06
    Activations Density 0.033%

    No Known Activations