© 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. 7925
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron detects quantitative measurement or comparison phrases (e.g. sizes, weights, areas).

    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
     ess
    -0.06
    less
    -0.06
     wary
    -0.06
     Profit
    -0.06
     cds
    -0.06
     aument
    -0.06
    	column
    -0.06
     рам
    -0.06
    	result
    -0.06
     nature
    -0.06
    POSITIVE LOGITS
     resemble
    0.06
    ondheim
    0.06
     LocalDate
    0.06
     JSONArray
    0.06
     yabancı
    0.06
    časí
    0.06
     resembled
    0.06
    Nor
    0.06
    ocos
    0.06
     generals
    0.06
    Activations Density 0.076%

    No Known Activations